Harbinzzy/All-in-One-Image-Restoration-Survey

[IEEE TPAMI 2025] A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

603

219 commits

updated Sep 27, 2026

See the code

README

A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

Junjun Jiang, Zengyuan Zuo,Gang Wu, Kui Jiang and Xianming Liu

AIIA Lab, Harbin Institute of Technology.

📚 Overview

Awesome-AiOIR-Methods
2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026
Awesome-AiOIR-Benchmarks
Three Challenging Datasets | Five Challenging Datasets | All-Weather | Real-World Weather-Related | CDD-11 | FoundIR's Datasets
Citations | Contributing

📢 News

✅ Our comprehensive survey paper on All-in-One Image Restoration has been released and is actively maintained.
📝 Submitted on 19 Oct 2024 (v1), last revised on 12 Jun 2025 (v2) with major updates and reductions.
We will continue to reflect the latest advancements in this evolving field. (IEEE TPAMI 25)

📖 All-in-one Image Restoration Paper List

2026

Paper	Avenue	Link	Code
Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration _{Xinyao Wang, Lijun He, Zhihan Ren, Fan Li}	arXiv	Paper
ImIR: Image-Instruction Tuning for All-in-One Image Restoration _{Süleyman Aslan, Görkay Aydemir, Mısra Yavuz, Yunus Bilge Kurt, Nasrin Rahimi, Ahmet Rasim Emirdağı, Burak Can Biner, M. Akın Yılmaz}	ACCV 2026	Paper
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration _{Hu Gao, Lizhuang Ma, Yulong Chen}	arXiv	Paper
UniH³: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration _{Zhiwen Yang, Jiayin Li, Chengyu Liu, Hui Zhang, Bingzheng Wei, Yan Xu}	ECCV 2026	Paper	Code
MARR: Decoupling Policy, Execution, and Calibration for All-in-One Medical Image Restoration _{Haobin Chen, Ao Chang, Heqin Zhu, Rundong Wang, Ting Liu, Shaohua Kevin Zhou}	arXiv	Paper	Code
Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network _{Zheke Jin, Yuning Cui, Tianle Jin, Alois Knoll, Hu Cao}	arXiv	Paper
DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration _{Zhaokun He, Kangbiao Shi, Axi Niu, Jian Jin, Peng Wu, Wei Dong, Qingsen Yan}	arXiv	Paper
Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance _{Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng}	ACM MM 2026	Paper
Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal _{Wanshu Fan, Yunzhe Zhang, Yue Shen, Liyan Wang, Jing Qin, Kin-Man Lam, Cong Wang, Jinshan Pan}	TIP 2026	Paper	Code
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration _{Zihao He, Yunfeng Wu, Xinchao Wang, Songhua Liu}	ICML 2026	Paper
SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning _{Shengkai Hu, Jie Shao, Jiaqi Ma, Xu Zhang, Keying Wu, Qilu Zhu, Beihang Song, Jun Wan}	arXiv	Paper
MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration _{Yongcong Wang, Pu Wang, Hingchin Chen, Runci Bai, Yucheng Xin, Chen Wu, Chengchao Shen, Guangwei Gao, Siyuan Yao, Pengwen Dai, Zhuoran Zheng}	arXiv	Paper
What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration _{Cencen Liu, Wen Yin, Dongyang Zhang, Dongmin Li, Shan Zhao, Bing Su, Tao He, Jielei Wang, Guoming Lu}	arXiv	Paper
CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration _{Zaiyan Zhang, Qiangqiang Yuan, Jie Li, Ziyang Lihe, Yu Wan, Yuzeng Chen, Xin Su, Liangpei Zhang}	ISPRS 2026	Paper	Code
Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents _{Hu Gao, Yulong Chen, Lizhuang Ma}	arXiv	Paper
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback _{Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun Fu}	CVPR 2026
IAMAgent: Toward an Interactive and Adaptive Multi-Agent System for Image Restoration _{Yanyan Wei, Yilin Zhang, Zhao Zhang, Huan Zheng, Jiahuan Ren, Xiaogang Xu, Meng Wang, Zenglin Shi}	TIP 2026	Paper
QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration _{Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian, Zhen Wu, Guangwen Peng, Zhiyuan Li, Ding Ding, Dian Shen, Fang Dong}	ACM MM 2026	Paper	Code
Virtual Consistency Model for All-in-one Image Restoration _{Jiawei Wu, Luwei Tu, Zhe Wang, Zhi Jin, Kaihao Zhang, Wenqi Ren, Xiaochun Cao}	TIP 2026	Paper
Transformer-Inspired Convolutional Network for Image Restoration _{Yuning Cui, Mingyu Liu, Wenqi Ren, Boxin Shi, Alois Knoll}	TCSVT 2026	Paper
Prompt-In-Prompt Learning for Universal Image Restoration _{Zilong Li, Yiming Lei, Chenglong Ma, Junping Zhang, Hongming Shan}	PR 2026	Paper	Code
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration _{Zihao He, Yunfeng Wu, Xinchao Wang, Songhua Liu}	ICML 2026	Paper
Hierarchical Physical-Chain Decoupling With Geo-Semantic MoLoRA for All-in-One Multimodal Remote Sensing Image Restoration _{Zhentao Zou, Jichu Zhan, Yue Zhou, Ran Ding, Jia Fu, Chaofeng Chen, Jianxin Xing, Xiaogang Yu, Xue Jiang}	TGRS 2026	Paper	Code
Learning Dual Transformers for All-in-One Image Restoration From a Frequency Perspective _{Jie Chu, Tong Su, Pei Liu, Yunpeng Wu, Le Zhang, Zenglin Shi, Meng Wang}	TNNLS 2026	Paper
Learning Adaptive Dynamical Features via Multi-τ Liquid-Mamba for All-in-one Image Restoration _{Hu Gao, Changshuo Wang, Yulong Chen, Lizhuang Ma}	arXiv	Paper
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration _{Yanjie Tu, Qingsen Yan, Axi Niu, Tao Hu, Haokui Zhang, Jiantao Zhou}	arXiv	Paper	Code
Universal Image Restoration via Internalized Chain-of-Thought Reasoning _{Yu Guo, Zhengru Fang, Shengfeng He, Senkang Hu, Yihang Tao, Phone Lin, Yuguang Fang}	arXiv	Paper	Code
DDTNet: Degradation Disentanglement and Transfer Network for Test-Time All-in-One De-weathering Adaptation _{Kuan-Hung Lin, Fu-Jen Tsai, Yan-Tsung Peng, Min-Hung Chen, Chia-Wen Lin, Yen-Yu Lin}	arXiv	Paper
Hierarchical Physical-Chain Decoupling With Geo-Semantic MoLoRA for All-in-One Multimodal Remote Sensing Image Restoration _{Zhentao Zou, Jichu Zhan, Yue Zhou, Ran Ding, Jia Fu, Chaofeng Chen, Jianxin Xing, Xiaogang Yu, Xue Jiang}	TGRS 2026	Paper	Code
Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration _{Ni Tang, Shenghao Nie, Xiaotong Luo, Yuan Xie, Yanyun Qu}	CVPR 2026	Paper
Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank _{Chenxu Wang, Kai Zhang, Jian Yang}	CVPR 2026	Paper	Code
DiTTo: Scalable Order-aware All-in-One Image Restoration Agent _{Seungho Choi, Jihyong Oh}	arXiv	Paper	Code
OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization _{Feng Zhu, Shuyang Xie, Yihan Zeng, Ming Liu, Wangmeng Zuo}	arXiv	Paper	Code
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration _{Xinghua Huang, Zhixiong Yang, Chen Wu, Shengxi Li, Shuaifeng Zhi, Yue Zhang, Qibin Hou, Xin Deng, Jingyuan Xia}	arXiv	Paper
Expandable, Compressible, Mineable: Open-World Thermal Image Restoration _{Pu Li, Huafeng Li, Yafei Zhang, Wen Wang, Neng Dong, Jie Wen}	ICML 2026	Paper	Code
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts _{Eunho Lee, Rei Kawakami, Youngbae Hwang}	arXiv	Paper
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization _{Ao Li, Xiaoning Liu, Sheng Li, Yapeng Du, Zhen Long, Lei Luo, Le Zhang, Ce Zhu}	TMM 2026	Paper	Code
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration _{Haisen He, Xiangyu Zou, SongLin Dong, Heng Li, Yihong Gong, Zhiheng Ma}	arXiv	Paper
PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow _{Wei Dong, Han Zhou, Terry Ji, Guanhua Zhao, Shahab Asoodeh, Yulun Zhang, Guangtao Zhai, Jun Chen, Xiaohong Liu}	arXiv	Paper	Code
UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement _{Weiqi Li, Xuanyu Zhang, Bin Chen, Jingfen Xie, Yan Wang, Kexin Zhang, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao}	arXiv	Paper	Code
Residual Diffusion Bridge Model for Image Restoration _{Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du}	CVPR 2026	Paper	Code
Hybrid Agents for Image Restoration _{Bingchen Li, Xin Li, Yiting Lu, Zhibo Chen}	CVPR 2026	Paper
UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration _{Zihan Cheng, Liangtai Zhou, Dian Chen, Ni Tang, Xiaotong Luo, Yanyun Qu}	CVPR 2026	Paper
FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration _{Jingren Liu, Shuning Xu, Qirui Yang, Yun Wang, Xiangyu Chen, Zhong Ji}	CVPR 2026	Paper	Code
FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model _{Xiang Chen, Jinshan Pan, Jiangxin Dong, Jian Yang, Jinhui Tang}	CVPR 2026	Paper	Code
Degradation-Aware Adaptive Context Gating for Unified Image Restoration _{Lei He, Jielei Chu, Fengmao Lv, Weide Liu, Tianrui Li, Jun Cheng, Yuming Fang}	arXiv	Paper	Code
Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement _{Pu Li, Huafeng Li, Yafei Zhang, Yu Liu, Wen Wang}	CVPR 2026	Paper	Code
LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results _{Xiang Chen, Hao Li, Jiangxin Dong, Jinshan Pan, et al.}	CVPR Workshops 2026	Paper
CDIR: LoRA-Inspired Attention for Efficient Composite Degradation Image Restoration _{Yuning Cui, Wenqi Ren, Boxin Shi, Jianhou Gan, Alois Knoll}	TIP 2026	Paper
A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting _{Yongchuan Cui, Peng Liu}	arXiv	Paper	Code
RIRF: Reasoning Image Restoration Framework _{Wending Yan, Rongkai Zhang, Kaihua Tang, Yu Cheng, Qiankun Liu}	arXiv	Paper
WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression _{Weikai Qu, Sijun Liang, Cheng Pan, Zikuan Yang, Guanchi Zhou, Xianjun Fu, Bo Liu, Changmiao Wang, Ahmed Elazab}	TAI 2026	Paper	Code
Task-Guided Prompting for Unified Remote Sensing Image Restoration _{Wenli Huang, Yang Wu, Xiaomeng Xin, Zhihong Liu, Jinjun Wang, Ye Deng}	TGRS 2026	Paper	Code
Your Pre-trained Diffusion Model Secretly Knows Restoration _{Sudarshan Rajagopalan, Vishal M. Patel}	arXiv	Paper	Code
A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting _{Yongchuan Cui, Peng Liu}	arXiv	Paper	Code
TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration _{Yisheng Zhang, Guoli Jia, Haote Hu, Shanxu Zhao, Kaikai Zhao, Long Sun, Xinwei Long, Kai Tian, Che Jiang, Zhaoxiang Liu, Kai Wang, Shiguo Lian, Kaiyan Zhang, Bowen Zhou}	arXiv	Paper
Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration _{I-Hsiang Chen, Isma Hadji, Enrique Sanchez, Adrian Bulat, Sy-Yen Kuo, Radu Timofte, Georgios Tzimiropoulos, Brais Martinez}	CVPR 2026	Paper	Code
Focal Modulation for Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	IJCV 2026	Paper	Code
StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion _{Yuning Cui, Syed Waqas Zamir, Ming-Hsuan Yang, Alois Knoll, Fahad Shahbaz Khan, Salman Khan}	TPAMI 2026	Paper	Code
Visual-in-Visual: A Unified and Efficient Baseline for Image Restoration _{Yuning Cui, Wenqi Ren, Boxin Shi, Alois Knoll}	TPAMI 2026	Paper
M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts _{Shiwei Wang, Yongzhen Wang, Bingwen Hu, Liyan Zhang, Xiao-Ping Zhang, Mingqiang Wei}	arXiv	Paper	Code
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration _{Debabrata Mandal, Soumitri Chattopadhyay, Yujie Wang, Marc Niethammer, Praneeth Chakravarthula}	arXiv	Paper
SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration _{Peng Shurui, Xin Lin, Shi Luo, Jincen Ou, Dizhe Zhang, Lu Qi, Truong Nguyen, Chao Ren}	arXiv	Paper
All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network _{Bingnan Wang, Bin Qin, Jiangmeng Li, Fanjiang Xu, Fuchun Sun, Hui Xiong}	TIP 2026	Paper
Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration _{Guanglu Dong, Chunlei Li, Chao Ren, Jingliang Hu, Yilei Shi, Xiao Xiang Zhu, Lichao Mou}	ICLR 2026	Paper	Code
MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration _{Lingshun Kong, Jiawei Zhang, Zhengpeng Duan, Xiaohe Wu, Yueqi Yang, Xiaotao Wang, Dongqing Zou, Lei Lei, Jinshan Pan}	arXiv	Paper	Code
Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration _{Xiaole Tang, Xiaoyi He, Jiayi Xu, Xiang Gu, Jian Sun}	TPAMI 2026	Paper	Code
PromptHSI: Universal Hyperspectral Image Restoration Framework for Composite Degradation _{Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin, Yi-Ching Cheng, Wo-Ting Liao, Chih-Chung Hsu, Fu-En Yang, Yu-Chiang Frank Wang}	TGRS 2026	Paper	Code
HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression _{Xiangming Wang, Benteng Sun, Yungeng Liu, Haijin Zeng, Yongyong Chen, Jingyong Su, Jie Liu}	arXiv	Paper	Code
Bridging Degradation Discrimination and Generation for Universal Image Restoration _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Yanye Lu}	ICLR 2026	Paper	Code
Vision-Language Controlled Deep Unfolding for Joint Medical Image Restoration and Segmentation _{Ping Chen, Zicheng Huang, Xiangming Wang, Yungeng Liu, Bingyu Liang, Haijin Zeng, Yongyong Chen}	arXiv	Paper	Code
DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library _{Shihong Liu, Kun Zuo, Hanguang Xiao}	ICASSP 2026	Paper
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration _{Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin}	arXiv	Paper
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration _{Yanjie Tu, Qingsen Yan, Axi Niu, Jiacong Tang}	arXiv	Paper	Code
From Physical Degradation Models to Task-Aware All-in-One Image Restoration _{Hu Gao, Xiaoning Lei, Xichen Xu, Xingjian Wang, Lizhuang Ma}	arXiv	Paper
Edit2Restore: Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models _{M. Akın Yılmaz, Ahmet Bilican, Burak Can Biner, A. Murat Tekalp}	arXiv	Paper	Code
UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing _{Zengyuan Zuo, Junjun Jiang, Gang Wu, Xianming Liu}	arXiv	Paper	Code
ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration _{Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang}	AAAI 2026	Paper	Code
Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration _{Jiawei Wu, Zhifei Yang, Zhe Wang, Zhi Jin}	AAAI 2026	Paper	Code
EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion _{Tong Chen, Xinyu Ma, Long Bai, Wenyang Wang, Yue Sun, Luping Zhou}	AAAI 2026	Paper	Code

2025

Paper	Avenue	Link	Code
Enhancing Image Restoration Transformer via Adaptive Translation Equivariance _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Hangzhou He, Yanye Lu}	ICCV 2025	Paper
Degradation-Aware Prompted Transformer for Unified Medical Image Restoration _{Jinbao Wei, Gang Yang, Zhijie Wang, Shimin Tao, Aiping Liu, Xun Chen}	TIP 2025	Paper	Code
SimpleCall: A Lightweight Image Restoration Agent in Label-Free Environments with MLLM Perceptual Feedback _{Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun Fu}	arXiv	Paper
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration _{Binfeng Wang, Di Wang, Haonan Guo, Ying Fu, Jing Zhang}	arXiv	Paper	Code
TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration _{Zhiwen Yang, Jiaju Zhang, Yang Yi, Jian Liang, Bingzheng Wei, Yan Xu}	MICCAI 2025	Paper	Code
DSwinIR: Rethinking Window-Based Attention for Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TPAMI 2025	Paper	Code
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration	TIP 2025	Paper
ClusIR: Towards Cluster-Guided All-in-One Image Restoration _{Shengkai Hu, Jiaqi Ma, Jun Wan, Wenwen Min, Yongcheng Jing, Lefei Zhang, Dacheng Tao}	arXiv	Paper
Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration _{Wenlong Jiao, Heyang Lee, Ping Wang, Pengfei Zhu, Qinghua Hu, Dongwei Ren}	arXiv	Paper	Code
EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulation _{Jiaqi Ma, Shengkai Hu, Jun Wan, Jiaxing Huang, Lefei Zhang, Salman Khan}	arXiv	Paper
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TPAMI 2025	Paper	Code
Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation _{Hu Gao, Xiaoning Lei, Ying Zhang, Xichen Xu, Guannan Jiang, Lizhuang Ma}	arXiv	Paper
Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution _{Hu Gao, Xiaoning Lei, Xichen Xu, Depeng Dang, Lizhuang Ma}	arXiv	Paper
MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration _{Tao Wang, Peiwen Xia, Bo Li, Peng-Tao Jiang, Zhe Kong, Kaihao Zhang, Tong Lu, Wenhan Luo}	ICCV 2025	Paper
Bio-Inspired Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	NeurIPS 2025	Paper	Code
A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks _{Xiaoxuan Gong, Jie Ma}	NeurIPS 2025	Paper
Residual Diffusion Bridge Model for Image Restoration _{Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du}	arXiv	Paper	Code
UniUIR: Considering Underwater Image Restoration as An All-in-One Learner _{Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang, Bo Du}	TIP 2025	Paper	Code
Frequency-Prompted Image Restoration to Enhance Perception in Intelligent Transportation Systems _{Yuning Cui, Mingyu Liu, Xiongfei Su, Alois Knoll}	TITS 2025	Paper
Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration _{Thomas Katraouras, Dimitrios Rafailidis}	WI-IAT 2025	Paper	Code
Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement _{Yidi Liu, Xueyang Fu, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Zheng-Jun Zha}	NeurIPS 2025	Paper	Code
UHD-Processor: Unified UHD Image Restoration with Progressive Frequency Learning and Degradation-aware Prompts _{Yidi Liu, Xueyang Fu, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Zheng-Jun Zha}	CVPR 2025	Paper	Code
Universal Image Restoration Pre-training via Masked Degradation Classification _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Yinghao Chen, Yanye Lu}	arXiv	Paper	Code
Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation _{Vijay M. Galshetwar, Praful Hambarde, Prashant W. Patil, Akshay Dudhane, Sachin Chaudhary, Santosh Kumar Vipparathi, Subrahmanyam Murala}	arXiv	Paper	Code
PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration _{Zhe Dong, Yuzhe Sun, Haochen Jiang, Tianzhu Liu, Yanfeng Gu}	arXiv	Paper	Code
Orochi: Versatile Biomedical Image Processor _{Gaole Dai, Chenghao Zhou, Yu Zhou, Rongyu Zhang, Yuan Zhang, Chengkai Hou, Tiejun Huang, Jianxu Chen, Shanghang Zhang}	NeurIPS 2025	Paper
Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding _{S M A Sharif, Abdur Rehman, Fayaz Ali Dharejo, Radu Timofte, Rizwan Ali Naqvi}	arXiv	Paper	Code
JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration _{Yunlong Lin, Zixu Lin, Haoyu Chen, Panwang Pan, Chenxin Li, Sixiang Chen, Kairun Wen, Yeying Jin, Wenbo Li, Xinghao Ding}	CVPR 2025	Paper	Code
RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration _{Zilong Zhang, Chujie Qin, Chunle Guo, Yong Zhang, Chao Xue, Ming-Ming Cheng, Chongyi Li}	arXiv	Paper	Code
WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration _{Qiyuan Guan, Qianfeng Yang, Xiang Chen, Tianyu Song, Guiyue Jin, Jiyu Jin}	ACMMM 2025	Paper	Code
Modumer: Modulating Transformer for Image Restoration _{Yuning Cui, Mingyu Liu, Wenqi Ren, Alois Knoll}	TNNLS 2025	Paper
TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal _{Hanting Wang, Shengpeng Ji, Shulei Wang, Hai Huang, Xiao Jin, Qifei Zhang, Tao Jin}	arXiv	Paper
Diffusion Once and Done: Degradation‑Aware LoRA for Efficient All‑in‑One Image Restoration _{Ni Tang, Xiaotong Luo, Zihan Cheng, Liangtai Zhou, Dongxiao Zhang, Yanyun Qu}	arXiv	Paper
Exploiting Diffusion Prior for Task-driven Image Restoration _{Jaeha Kim, Junghun Oh, Kyoung Mu Lee}	ICCV 2025	Paper	Code
Robust Adverse Weather Removal via Spectral-based Spatial Grouping _{Yuhwan Jeong, Yunseo Yang, Youngjo Yoon, Kuk-Jin Yoon}	ICCV 2025	Paper	Code
All-in-One Medical Image Restoration with Latent Diffusion-Enhanced Vector-Quantized Codebook Prior _{Haowei Chen, Zhiwen Yang, Haotian Hou, Hui Zhang, Bingzheng Wei, Gang Zhou, Yan Xu}	MICCAI 2025	Paper
Exploring Scalable Unified Modeling for General Low-Level Vision _{Xiangyu Chen, Kaiwen Zhu, Yuandong Pu, Shuo Cao, Xiaohui Li, Wenlong Zhang, Yihao Liu, Yu Qiao, Jiantao Zhou, Chao Dong}	arXiv	Paper
Exploring the Potential of Pooling Techniques for Universal Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	TIP 2025	Paper	Code
4KAgent: Agentic Any Image to 4K Super-Resolution _{Yushen Zuo, Qi Zheng, Mingyang Wu, Xinrui Jiang, Renjie Li, Jian Wang, Yide Zhang, Gengchen Mai, Lihong V. Wang, James Zou, Xiaoyu Wang, Ming-Hsuan Yang, Zhengzhong Tu}	NeurIPS 2025	Paper	Code
Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration _{Xin Lu, Xueyang Fu, Jie Xiao, Zihao Fan, Yurui Zhu, Zheng-Jun Zha}	arXiv	Paper	Code
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling _{Huaqiu Li, Yong Wang, Tongwen Huang, Hailang Huang, Haoqian Wang, Xiangxiang Chu}	arXiv	Paper	Code
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration _{Hao Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan}	ICCV 2025	Paper	Code
UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior _{I-Hsiang Chen, Wei-Ting Chen, Yu-Wei Liu, Yuan-Chun Chiang, Sy-Yen Kuo, Ming-Hsuan Yang}	CVPR 2025	Paper	Code
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration _{Haina Qin, Wenyang Luo, Zewen Chen, Yufan Liu, Bing Li, Weiming Hu, libin wang, DanDan Zheng, Yuming Li}	CVPR 2025	Paper	Code
UniRes: Universal Image Restoration for Complex Degradations	arXiv	Paper
Boosting All-in-One Image Restoration via Self-Improved Privilege Learning	arXiv	Paper	Code
Navigating Image Restoration with VAR's Distribution Alignment Prior _{Siyang Wang, Feng Zhao}	arXiv	Paper	Code
From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration _{Junyu Fan, Chuanlin Liao, Yi Lin}	arXiv	Paper
Manifold-aware Representation Learning for Degradation-agnostic Image Restoration _{Bin Ren, Yawei Li, Xu Zheng, Yuqian Fu, Danda Pani Paudel, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe}	arXiv	Paper	Code
Learning Dynamic Prompts for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TIP 2025	Paper	Code
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery _{Hainuo Wang, Qiming Hu, Xiaojie Guo}	arXiv	Paper	Code
Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration _{Yuetong Liu, Yunqiu Xu, Yang Wei, Xiuli Bi, Bin Xiao}	arXiv	Paper	Code
RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration _{Sudarshan Rajagopalan, Kartik Narayan, Vishal M. Patel}	arXiv	Paper	Code
All-in-One Weather-Degraded Image Restoration Via Adaptive Degradation-Aware Self-Prompting Model _{Yuanbo Wen, Tao Gao, Ziqi Li, Jing Zhang, Kaihao Zhang, Ting Chen}	TMM 2025	Paper
AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning _{Sudarshan Rajagopalan, Vishal M. Patel}	AAAI 2025	Paper	Code
CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture _{Vladimir Frants, Sos Agaian, Karen Panetta, Peter Huang}	arXiv	Paper
DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model _{Zhanwen Liu, Sai Zhou, Yuchao Dai, Yang Wang, Yisheng An, Xiangmo Zhao}	arXiv	Paper
Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation _{Bin Ren, Eduard Zamfir, Zongwei Wu, Yawei Li, Yidi Li, Danda Pani Paudel, Radu Timofte, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe}	arXiv	Paper	Code
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	arXiv	Paper	Code
Beyond Degradation Conditions: All-in-One Image Restoration via HOG Transformers _{Jiawei Wu, Zhifei Yang, Zhe Wang, Zhi Jin}	arXiv	Paper	Code
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision _{Yuandong Pu, Le Zhuo, Kaiwen Zhu, Liangbin Xie, Wenlong Zhang, Xiangyu Chen, Peng Gao, Yu Qiao, Chao Dong, Yihao Liu}	arXiv	Paper	Code
Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration _{Yuanbo Wen, Tao Gao, Jing Zhang, Ziqi Li, Ting Chen}	AAAI 2025	Paper	Code
VL-UR: Vision-Language-guided Universal Restoration of Images Degraded by Adverse Weather Conditions _{Ziyan Liu, Yuxu Lu, Huashan Yu, Dong Yang}	arXiv	Paper
Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model _{Yingjie Zhou, Jiezhang Cao, Zicheng Zhang, Farong Wen, Yanwei Jiang, Jun Jia, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai}	arXiv	Paper
DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration _{Jiamei Xiong, Xuefeng Yan, Yongzhen Wang, Wei Zhao, Xiao-Ping Zhang, Mingqiang Wei}	arXiv	Paper
Content-Aware Transformer for All-in-one Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu}	arXiv	Paper	Code
Cat-AIR: Content and Task-Aware All-in-One Image Restoration _{Jiachen Jiang, Tianyu Ding, Ke Zhang, Jinxin Zhou, Tianyi Chen, Ilya Zharkov, Zhihui Zhu, Luming Liang}	arXiv	Paper	Code
UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations _{Debabrata Mandal, Soumitri Chattopadhyay, Guansen Tong, Praneeth Chakravarthula}	arXiv	Paper	Code
Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal _{Rongxin Liao, Feng Li, Yanyan Wei, Zenglin Shi, Le Zhang, Huihui Bai, Meng Wang}	arXiv	Paper	Code
TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Models _{Wanglong Lu, Lingming Su, Jingjing Zheng, Vinícius Veloso de Melo, Farzaneh Shoeleh, John Hawkin, Terrence Tricco, Hanli Zhao, Xianta Jiang}	arXiv	Paper
Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks _{Haijin Zeng, Xiangming Wang, Yongyong Chen, Jingyong Su, Jie Liu}	CVPR2025	Paper	Code
Degradation-Aware Feature Perturbation for All-in-One Image Restoration _{Xiangpeng Tian, Xiangyu Liao, Xiao Liu, Meng Li, Chao Ren}	CVPR2025	Paper	Code
Multi-Agent Image Restoration _{Xu Jiang, Gehui Li, Bin Chen, Jian Zhang}	arXiv	Paper
MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration _{Zhehui Wu, Yong Chen, Naoto Yokoya, Wei He}	arXiv	Paper	Code
Dynamic Degradation Decomposition Network for All-in-One Image Restoration _{Huiqiang Wang, Mingchen Song, Guoqiang Zhong}	arXiv	Paper
USRNet: Unified Scene Recovery Network for Enhancing Traffic Imaging under Multiple Adverse Weather Conditions _{Yuxu Lu, Ai Chen, Dong Yang, Ryan Wen Liu}	arXiv	Paper	Code
Up-Restorer: When Unrolling Meets Prompts for Unified Image Restoration _{Minghao Liu, Wenhan Yang, Jinyi Luo, Jiaying Liu}	AAAI2025	Paper
Debiased All-in-one Image Restoration with Task Uncertainty Regularization _{Gang Wu, Junjun Jiang, Yijun Wang, Kui Jiang, Xianming Liu}	AAAI2025	Paper	Code
All-in-One Image Compression and Restoration _{Huimin Zeng, Jiacheng Li, Ziqiang Zheng, Zhiwei Xiong}	WACV2025	Paper	Code
RamIR: Reasoning and action prompting with Mamba for all-in-one image restoration _{Aiqiang Tang, Yan Wu, Yuwei Zhang}	Applied Intelligence	Paper
Universal Image Restoration Pre-training via Degradation Classification _{JiaKui Hu, Lujia Jin, Zhengjian Yao, Yanye Lu}	ICLR2025	Paper	Code
Complexity Experts are Task-Discriminative Learners for Any Image Restoration _{Eduard Zamfir, Zongwei Wu, Nancy Mehta, Yuedong Tan, Danda Pani Paudel, Yulun Zhang, Radu Timofte}	CVPR2025	Paper	Code
Adaptive Blind All-in-One Image Restoration _{David Serrano-Lozano, Luis Herranz, Shaolin Su, Javier Vazquez-Corral}	arXiv	Paper	Code
GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration _{Sudarshan Rajagopalan, Nithin Gopalakrishnan Nair, Jay N. Paranjape, Vishal M. Patel}	CVPR2025	Paper	Code
OmniRestore: Robust Universal Image Restoration from Combined and Unspecified Degradations _{Anjusree Karnavar, Yang Li, Jiajun Liu, Jun Zhou, Junhu Wang}	ICME 2025	Paper

2024

Paper	Avenue	Link	Code
Reference-Based Multi-Stage Progressive Restoration for Multi-Degraded Images _{Yi Zhang, Qixue Yang, Damon M. Chandler, Xuanqin Mou}	TIP 2024	Paper	Code
IPT-ILR: Image Pyramid Transformer Coupled With Information Loss Regularization for All-in-One Image Restoration _{Sai Yang, Bin Hu, Fan Liu, Xiaoxin Wu, Weiping Ding, Jun Zhou}	TCSVT 2024	Paper
Omni-Kernel Modulation for Universal Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	TCSVT 2024	Paper
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity _{Jingbo Lin, Zhilu Zhang, Wenbo Li, Renjing Pei, Hang Xu, Hongzhi Zhang, Wangmeng Zuo}	arXiv	Paper	Code
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation _{Aiwen Jiang, Hourong Chen, Zhiwen Chen, Jihua Ye, Mingwen Wang}	arXiv	Paper	Code
MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers _{Ruoxi Zhu, Zhengzhong Tu, Jiaming Liu, Alan C. Bovik, Yibo Fan}	TIP2024	Paper	Code
Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding _{Yubin Gu, Yuan Meng, Xiaoshuai Sun, Jiayi Ji, Weijian Ruan, Rongrong Ji}	arXiv	Paper
AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations _{Jiawei Mao, Yu Yang, Xuesong Yin, Ling Shao, Hao Tang}	arXiv	Paper
All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Model _{Yuanbo Wen, Tao Gao, Ziqi Li, Jing Zhang, Kaihao Zhang, Ting Chen}	arXiv	Paper
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration _{Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun}	TPAMI2025	Paper	Code
Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers _{Jin Cao, Deyu Meng, Xiangyong Cao}	arXiv	Paper	Code
An Intelligent Agentic System for Complex Image Restoration Problems _{Kaiwen Zhu, Jinjin Gu, Zhiyuan You, Yu Qiao, Chao Dong}	ICLR2025	Paper	Code
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration _{Yuang Ai, Huaibo Huang, Ran He}	arXiv	Paper	Code
Adaptive Fuzzy Degradation Perception Based on CLIP Prior for All-in-One Image Restoration _{M. Shao, Y. Liu, Y. Cheng, Y. Wan, C. Wang}	IEEE Trans. Fuzzy Syst 2024	Paper
TANet: Triplet Attention Network for All-In-One Adverse Weather Image Restoration _{Hsing-Hua Wang, Fu-Jen Tsai, Yen-Yu Lin, Chia-Wen Lin}	ACCV2024	Paper	Code
Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration _{Chu-Jie Qin, Rui-Qi Wu, Zikun Liu, Xin Lin, Chun-Le Guo, Hyun Hee Park, Chongyi Li}	ECCV2024	Paper	Code
Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint _{Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, Lei Zhu}	ECCV2024	Paper	Code
Accurate Forgetting for All-in-One Image Restoration Model _{Xin Su, Zhuoran Zheng}	arXiv	Paper
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration _{Xu Zhang, Jiaqi Ma, Guoli Wang, Qian Zhang, Huan Zhang, Lefei Zhang}	TIP2025	Paper	Code
Learning A Low-Level Vision Generalist via Visual Task Prompt _{Xiangyu Chen, Yihao Liu, Yuandong Pu, Wenlong Zhang, Jiantao Zhou, Yu Qiao, Chao Dong}	ACMMM2024	Paper	Code
HAIR: Hypernetworks-based All-in-One Image Restoration _{Jin Cao, Yi Cao, Li Pang, Deyu Meng, Xiangyong Cao}	arXiv	Paper	Code
Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method _{Xin Su, Zhuoran Zheng, Chen Wu}	arXiv	Paper
UniProcessor: A Text-induced Unified Low-level Image Processor _{Huiyu Duan, Xiongkuo Min, Sijing Wu, Wei Shen, Guangtao Zhai}	ECCV2024	Paper	Code
Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration _{Xiaoyan Yu, Shen Zhou, Huafeng Li, Liehuang Zhu}	TCSVT 2024	Paper	Code
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models _{Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, Lei Zhu}	NIPS2024	Paper	Code
Training-Free Large Model Priors for Multiple-in-One Image Restoration _{Xuanhua He, Lang Li, Yingying Wang, Hui Zheng, Ke Cao, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, Man Zhou}	arXiv	Paper
Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration _{Yuhong Zhang, Hengsheng Zhang, Xinning Chai, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang}	arXiv	Paper	Code
Any Image Restoration with Efficient Automatic Degradation Adaptation _{Bin Ren, Eduard Zamfir, Yawei Li, Zongwei Wu, Danda Pani Paudel, Radu Timofte, Nicu Sebe, Luc Van Gool}	arXiv	Paper	Code
Restoring Images in Adverse Weather Conditions via Histogram Transformer _{Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, Xiaochun Cao}	ECCV 2024	Paper	Code
GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity _{Shuo Cao, Yihao Liu, Wenlong Zhang, Yu Qiao, Chao Dong}	ECCV2024	Paper
OneRestore: A Universal Restoration Framework for Composite Degradation _{Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He}	ECCV2024	Paper	Code
Learning Frequency-Aware Dynamic Transformers for All-In-One Image Restoration _{Zenglin Shi, Tong Su, Pei Liu, Yunpeng Wu, Le Zhang, Meng Wang}	arXiv	Paper
Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation _{Yuchuan Tian, Jianhong Han, Hanting Chen, Yuanyuan Xi, Guoyang Zhang, Jie Hu, Chao Xu, Yunhe Wang}	arXiv	Paper	Code
ConStyle v2: A Strong Prompter for All-in-One Image Restoration _{Dongqi Fan, Junhao Zhang, Liang Chang}	arXiv	Paper	Code
Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance _{Jiawei Mao, Juncheng Wu, Yuyin Zhou, Xuesong Yin, Yuanqi Chang}	arXiv	Paper	Code
All-In-One Medical Image Restoration via Task-Adaptive Routing _{Zhiwen Yang, Haowei Chen, Ziniu Qian, Yang Yi, Hui Zhang, Dan Zhao, Bingzheng Wei, Yan Xu}	MICCAI2024	Paper	Code
Efficient Degradation-aware Any Image Restoration _{Eduard Zamfir, Zongwei Wu, Nancy Mehta, Danda Pani Paudel, Yulun Zhang, Radu Timofte}	arXiv	Paper	Code
Harmony in Diversity: Improving All-in-One Image Restoration via Multi-Task Collaboration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu}	ACMMM2024	Paper	Code
Referring Flexible Image Restoration _{Runwei Guan, Rongsheng Hu, Zhuhao Zhou, Tianlang Xue, Ka Lok Man, Jeremy Smith, Eng Gee Lim, Weiping Ding, Yutao Yue}	arXiv	Paper	Code
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models _{Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön}	CVPRW2024	Paper	Code
Joint Conditional Diffusion Model for Image Restoration with Mixed Degradations _{Yufeng Yue, Meng Yu, Luojie Yang, Yi Yang}	arXiv	Paper
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration _{Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang}	arXiv	Paper	Code
WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal _{Yulin Luo, Rui Zhao, Xiaobao Wei, Jinwei Chen, Yijie Lu, Shenghao Xie, Tianyu Wang, Ruiqin Xiong, Ming Lu, Shanghang Zhang}	arXiv	Paper
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation _{Yuning Cui, Syed Waqas Zamir, Salman Khan, Alois Knoll, Mubarak Shah, Fahad Shahbaz Khan}	ICLR2025	Paper	Code
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks _{Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin}	CVPR 2024	Paper	Code
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model _{Dian Zheng, Xiao-Ming Wu, Shuzhou Yang, Jian Zhang, Jian-Fang Hu, Wei-Shi Zheng}	CVPR2024	Paper	Code
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure _{De Cheng, Yanling Ji, Dong Gong, Yan Li, Nannan Wang, Junwei Han, Dingwen Zhang}	TMM 2024	Paper	Code
AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration _{Yuxu Lu, Dong Yang, Yuan Gao, Ryan Wen Liu, Jun Liu, Yu Guo}	arXiv	Paper	Code
InstructIR: High-Quality Image Restoration Following Human Instructions _{Marcos V. Conde, Gregor Geigle, Radu Timofte}	ECCV2024	Paper	Code
Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration _{Yimin Xu, Nanxi Gao, Zhongyun Shan, Fei Chao, Rongrong Ji}	arXiv	Paper	Code
Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy _{Xiangtao Kong, Chao Dong, Lei Zhang}	arXiv	Paper	Code
Improving Image Restoration through Removing Degradations in Textual Representations _{Jingbo Lin, Zhilu Zhang, Yuxiang Wei, Dongwei Ren, Dongsheng Jiang, Wangmeng Zuo}	CVPR2024	Paper	Code
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation _{Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang}	AAAI2024	Paper	Code

2023

Paper	Avenue	Link	Code
Textual Prompt Guided Image Restoration _{Qiuhai Yan, Aiwen Jiang, Kang Chen, Long Peng, Qiaosi Yi, Chunjie Zhang}	arXiv	Paper	Code
Decoupling Degradation and Content Processing for Adverse Weather Image Restoration _{Xi Wang, Xueyang Fu, Peng-Tao Jiang, Jie Huang, Mi Zhou, Bo Li, Zheng-Jun Zha}	arXiv	Paper
Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration _{Yuang Ai, Huaibo Huang, Xiaoqiang Zhou, Jiexiang Wang, Ran He}	CVPR2024	Paper
Language-driven All-in-one Adverse Weather Removal _{Hao Yang, Liyuan Pan, Yan Yang, Wei Liang}	CVPR2024	Paper
Test-Time Degradation Adaptation for Open-Set Image Restoration _{Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao, Xi Peng}	ICML2024	Paper	Code
Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement _{Yanyan Wei, Zhao Zhang, Jiahuan Ren, Xiaogang Xu, Richang Hong, Yi Yang, Shuicheng Yan, Meng Wang}	arXiv	Paper
Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal _{Yu-Wei Chen, Soo-Chang Pei}	IEEE Access2025	Paper	Code
Neural Degradation Representation Learning for All-In-One Image Restoration _{Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong}	TIP2024	Paper
AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion _{Yitong Jiang, Zhaoyang Zhang, Tianfan Xue, Jinwei Gu}	ECCV2024	Paper	Code
Unifying Image Processing as Visual Prompting Question Answering _{Yihao Liu, Xiangyu Chen, Xianzheng Ma, Xintao Wang, Jiantao Zhou, Yu Qiao, Chao Dong}	ICML2024	Paper
Controlling Vision-Language Models for Universal Image Restoration _{Ziwei Luo, Zheng Zhao, Thomas B. Schön}	ICLR2024	Paper	Code
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction _{Bingyu Xin, Meng Ye, Leon Axel, Dimitris N. Metaxas}	STACOM2023	Paper	Code
Prompt-based Ingredient-Oriented All-in-One Image Restoration _{Hu Gao, Depeng Dang}	TCSVT2024	Paper
All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation _{Cheng Zhang, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang}	ACMMM2023	Paper
Decomposition Ascribed Synergistic Learning for Unified Image Restoration _{Jinghao Zhang, Feng Zhao}	arXiv	Paper
RDM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration _{Yuanshuo Cheng, Mingwen Shao, Yecong Wan, Chao Wang}	Knowledge-Based Systems2024	Paper	Code
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration _{Jiaqi Ma, Tianheng Cheng, Guoli Wang, Qian Zhang, Xinggang Wang, Lefei Zhang}	arXiv	Paper
PromptIR: Prompting for All-in-One Blind Image Restoration _{Vaishnav Potlapalli, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan}	NeurIPS2023	Paper	Code
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions _{Tao Wang, Kaihao Zhang, Ziqian Shao, Wenhan Luo, Bjorn Stenger, Tong Lu, Tae-Kyun Kim, Wei Liu, Hongdong Li}	IJCV2024	Paper	Code
Multi-task Image Restoration Guided By Robust DINO Features _{Xin Lin, Jingtong Yue, Kelvin C.K. Chan, Lu Qi, Chao Ren, Jinshan Pan, Ming-Hsuan Yang}	arXiv	Paper
Generative Diffusion Prior for Unified Image Restoration and Enhancement _{Ben Fei, Zhaoyang Lyu, Liang Pan, Junzhe Zhang, Weidong Yang, Tianyue Luo, Bo Zhang, Bo Dai}	CVPR2023	Paper	Code
Context-aware Pretraining for Efficient Blind Image Decomposition _{Chao Wang, Zhedong Zheng, Ruijie Quan, Yifan Sun, Yi Yang}	CVPR2023	Paper
Ingredient-oriented Multi-Degradation Learning for Image Restoration _{Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao}	CVPR2023	Paper
Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions _{Yurui Zhu, Tianyu Wang, Xueyang Fu, Xuanyu Yang, Xin Guo, Jifeng Dai, Yu Qiao, Xiaowei Hu}	CVPR2023	Paper	Code
Adverse Weather Removal with Codebook Priors _{Tian Ye, Sixiang Chen, Jinbin Bai, Jun Shi, Chenghao Xue, Jingxia Jiang, Junjie Yin, Erkang Chen, Yun Liu}	ICCV2023	Paper
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models _{Ozan Özdenizci, Robert Legenstein}	TPAMI2023	Paper
Images Speak in Images: A Generalist Painter for In-Context Visual Learning _{Xinlong Wang, Wen Wang, Yue Cao, Chunhua Shen, Tiejun Huang}	CVPR2023	Paper	Code

2022

Paper	Avenue	Link	Code
All-In-One Image Restoration for Unknown Corruption _{Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng}	CVPR2022	Paper	Code
TAPE: Task-Agnostic Prior Embedding for Image Restoration _{Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian}	CVPR2022	Paper
Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model _{Wei-Ting Chen, Zhi-Kai Huang, Cheng-Che Tsai, Hao-Hsiang Yang, Jian-Jiun Ding, Sy-Yen Kuo}	CVPR2022	Paper	Code
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions _{Jeya Maria Jose Valanarasu, Rajeev Yasarla, Vishal M. Patel}	CVPR2022	Paper	Code
Blind Image Decomposition _{Junlin Han, Weihao Li, Pengfei Fang, Chunyi Sun, Jie Hong, Mohammad Ali Armin, Lars Petersson, Hongdong Li}	ECCV2022	Paper	Code

2021

Paper	Avenue	Link	Code
On Efficient Transformer-Based Image Pre-training for Low-Level Vision _{Wenbo Li, Xin Lu, Shengju Qian, Jiangbo Lu, Xiangyu Zhang, Jiaya Jia}	arXiv	Paper	Code
Pre-Trained Image Processing Transformer _{Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao}	CVPR2021	Paper	Code

2020

Paper	Avenue	Link	Code
All in One Bad Weather Removal Using Architectural Search _{Ruoteng Li, Robby T. Tan, Loong-Fah Cheong}	CVPR2020	Paper
A General Decoupled Learning Framework for Parameterized Image Operators _{Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen}	TPAMI2019	Paper

📊 All-in-one Image Restoration Performance Comparison

Performance Comparisons of AiOIR Models on Three Challenging Datasets

Category	Method	Venue & Year	Params	Dehazing SOTS	Deraining Rain100L	Denoising σ=15	Denoising σ=25	Denoising σ=50	Average	Approach
Single	LPN	CVPR'19	3M	20.84/0.828	24.88/0.784	26.47/0.778	24.77/0.748	21.26/0.552	23.64/0.738	Specific
	ADFNet	AAAI'23	8M	28.13/0.961	34.24/0.965	33.76/0.929	30.83/0.871	27.75/0.793	30.94/0.904	Specific
	DehazeFormer	TIP'23	25M	29.58/0.970	35.37/0.969	33.01/0.914	30.14/0.858	27.37/0.779	31.09/0.898	Specific
	DRSformer	CVPR'23	34M	29.02/0.968	35.89/0.970	33.28/0.921	30.55/0.862	27.58/0.786	31.26/0.902	Specific
Multiple	MPRNet	CVPR'21	16M	28.00/0.958	33.86/0.958	33.27/0.920	30.76/0.871	27.29/0.761	30.63/0.894	General
	Restormer	CVPR'22	26M	27.78/0.958	33.78/0.958	33.72/0.865	30.67/0.865	27.63/0.792	30.75/0.901	General
	NAFNet	ECCV'22	17M	24.11/0.960	33.64/0.956	33.18/0.918	30.47/0.865	27.12/0.754	29.67/0.844	General
	FSNet	TPAMI'23	13M	29.14/0.969	35.61/0.969	33.81/0.874	30.84/0.872	27.69/0.762	31.42/0.906	General
	MambaIR	ECCV'24	27M	29.57/0.970	35.42/0.969	33.88/0.931	30.95/0.874	27.74/0.793	31.51/0.907	General
All-in-One	DL	TPAMI'19	2M	26.92/0.931	32.62/0.931	33.05/0.914	30.41/0.861	26.90/0.740	29.98/0.875	parameterized image operator
	TKMANet	CVPR'22	29M	30.41/0.973	34.94/0.972	33.02/0.924	30.31/0.820	23.80/0.556	30.50/0.849	two-stage knowledge learning
	AirNet	CVPR'22	9M	27.94/0.962	34.90/0.967	33.92/0.933	31.26/0.888	28.00/0.797	31.20/0.910	contrastive-based & degradation-guided
	PIP_restormer	arXiv'23	27M	32.09/0.981	38.29/0.984	34.24/0.936	31.60/0.893	28.35/0.806	32.91/0.920	prompt-in-prompt learning
	IDR	CVPR'23	15M	29.87/0.970	36.03/0.971	33.89/0.931	31.32/0.884	28.04/0.798	31.83/0.911	ingredient-oriented learning
	PromptIR	NeurIPS'23	36M	30.58/0.974	36.37/0.972	33.98/0.933	31.31/0.888	28.06/0.799	32.06/0.913	prompt for AiOIR
	Gridformer	IJCV'23	34M	30.37/0.970	37.15/0.972	33.93/0.931	31.37/0.887	28.11/0.801	32.19/0.912	transformer with grid structure
	ProRes	arXiv'23	371M	28.38/0.938	33.68/0.954	32.10/0.907	30.18/0.863	27.58/0.779	30.38/0.888	degradation-aware visual prompt
	NDR	TIP'24	28M	28.64/0.962	35.42/0.969	34.01/0.932	31.36/0.887	28.10/0.798	31.51/0.910	neural degradation representation
	Art_PromptIR	ACM MM'24	36M	30.83/0.979	37.94/0.982	34.06/0.934	31.42/0.891	28.14/0.801	32.49/0.917	via multi-task collaboration
	AnyIR	arXiv'24	6M	31.38/0.979	37.90/0.981	33.95/0.933	31.29/0.889	28.03/0.797	32.51/0.916	local-global gated intertwining
	DaAIR	arXiv'24	6M	32.30/0.981	37.10/0.978	33.92/0.930	31.26/0.884	28.00/0.792	32.51/0.913	efficient degradation-aware
	MEASNet	arXiv'24	31M	31.61/0.981	39.00/0.985	34.12/0.935	31.46/0.892	28.19/0.803	32.85/0.919	multi-expert adaptive selection
	U-WADN	arXiv'24	6M	29.21/0.971	35.36/0.968	33.73/0.931	31.14/0.886	27.92/0.793	31.47/0.910	unified-width adaptive network
	Shi et al.	arXiv'24	-	29.20/0.972	37.50/0.980	34.59/0.941	31.83/0.900	28.46/0.814	32.32/0.921	frequency-aware transformers
	DyNet	arXiv'24	16M	31.98/0.981	38.71/0.983	34.11/0.936	31.44/0.892	28.18/0.803	32.88/0.920	dynamic pre-training
	Hair	arXiv'24	29M	30.98/0.979	38.59/0.983	34.16/0.935	31.51/0.892	28.24/0.803	32.70/0.919	hypernetworks-based
	LoRA-IR	arXiv'24	-	30.68/0.961	37.75/0.979	34.06/0.935	31.42/0.891	28.18/0.803	32.42/0.914	mixture of low-rank experts
	Up-Restorer	AAAI'25	28M	30.68/0.977	36.74/0.978	33.99/0.933	31.33/0.888	28.07/0.799	32.16/0.915	ADMM-solver-based design
	TUR_PromptIR	AAAI'25	36M	31.17/0.978	38.57/0.984	34.06/0.932	31.40/0.887	28.13/0.797	32.67/0.916	a novel loss function
	AdaIR	ICLR'25	29M	31.06/0.980	38.64/0.983	34.12/0.935	31.45/0.892	28.19/0.802	32.69/0.918	frequency mining and modulation
	DA-RCOT	TPAMI'25	50M	31.26/0.977	38.36/0.983	33.98/0.934	31.33/0.890	28.10/0.801	32.60/0.917	as an optimal transport problem
	ABAIR	arXiv'24	41M	33.53/0.984	38.69/0.982	34.18/0.935	31.38/0.890	28.25/0.804	33.21/0.919	a three-phase approach
	MoCE-IR	CVPR'25	25M	31.34/0.979	38.57/0.984	34.11/0.932	31.45/0.888	28.18/0.800	32.73/0.917	mixture-of-complexity-experts
	MTAIR	arXiv'24	-	31.34/0.983	39.15/0.984	34.14/0.936	31.50/0.893	28.24/0.805	32.87/0.920	Mamba-Transformer cross-dimensional
	DCPT_PromptIR	ICLR'25	35M	31.91/0.981	38.43/0.983	34.17/0.933	31.53/0.889	28.30/0.802	32.87/0.918	learn to classify degradation
	RamIR	APPL INTELL'25	22M	31.29/0.977	38.16/0.981	34.04/0.931	31.61/0.891	28.19/0.801	32.65/0.916	prompt-driven Mamba-based
	Cat-AIR	arXiv'25	-	31.49/0.980	38.43/0.983	34.11/0.935	31.44/0.892	28.14/0.803	32.72/0.919	content and task-aware framework
	DSwinIR	arXiv'25	24M	31.86/0.980	37.73/0.983	34.12/0.933	31.59/0.890	28.31/0.803	32.72/0.917	deformable sliding window transformer
	CPL_PromptIR	arXiv'25	36M	31.27/0.980	38.77/0.985	34.15/0.933	31.50/0.889	28.23/0.800	32.78/0.917	contrastive prompt regularization
	AnyIR	arXiv'25	6M	31.75/0.981	38.61/0.984	34.12/0.936	31.46/0.893	28.20/0.804	32.83/0.920	local-global gated mechanism
	MIRAGE	arXiv'25	10M	31.86/0.981	38.94/0.985	34.12/0.935	31.46/0.891	28.19/0.803	32.91/0.919	within the SPD manifold space
	BaryIR	arXiv'25	-	31.33/0.980	38.95/0.984	34.16/0.935	31.54/0.892	28.25/0.802	32.85/0.919	in continuous barycenter space
	SIPL_PromptIR	arXiv'25	39M	31.09/0.977	38.43/0.984	34.12/0.933	31.48/0.889	28.22/0.800	32.67/0.917	privilege learning
	TextPromptIR	arXiv'23	124M+110M	31.65/0.978	38.41/0.982	34.17/0.936	31.52/0.893	28.26/0.805	32.80/0.919	textual prompt for AiOIR
	InstructIR-3D	ECCV'24	16M+17M	30.22/0.959	37.98/0.978	34.15/0.933	31.52/0.890	28.30/0.804	32.43/0.913	natural language prompts
	DA-CLIP_IR-SDE	ICLR'24	49M+125M	26.83/0.962	35.85/0.972	31.43/0.889	25.05/0.605	18.33/0.308	27.50/0.747	degradation-aware vision-language model
	Perceive-IR	arXiv'24	42M+86M	30.87/0.975	38.29/0.980	34.13/0.934	31.42/0.888	28.09/0.797	32.56/0.915	prompt-based foundation model
	VLU-Net	CVPR'25	35M+88M	30.71/0.980	38.93/0.984	34.13/0.935	31.48/0.892	28.23/0.804	32.70/0.919	vision-language gradient descent-driven
	DFPIR	CVPR'25	31M+63M	31.87/0.980	38.65/0.982	34.14/0.935	31.47/0.893	28.25/0.806	32.88/0.919	degradation-aware feature perturbation

Performance Comparisons of AiOIR Models on Five Challenging Datasets

Type	Method	Venue & Year	Params	Dehazing (SOTS)	Deraining (Rain100L)	Denoising (BSD68)	Deblurring (Gopro)	Low-light (LOL)	Average	Approach
Single	ADFNet	AAAI'23	8M	24.18 / 0.928	32.97 / 0.943	31.15 / 0.882	25.79 / 0.781	21.15 / 0.823	27.05 / 0.871	Specific
	DehazeFormer	TIP'23	25M	25.31 / 0.937	33.68 / 0.954	30.89 / 0.880	25.93 / 0.785	21.31 / 0.819	27.42 / 0.875	Specific
	DRSformer	CVPR'23	34M	24.66 / 0.931	33.45 / 0.953	30.97 / 0.881	25.56 / 0.780	21.77 / 0.821	27.28 / 0.873	Specific
	HI-Diff	NeurIPS'23	24M	25.09 / 0.935	33.26 / 0.951	30.61 / 0.878	26.48 / 0.800	22.01 / 0.870	27.49 / 0.887	Specific
	Retinexformer	ICCV'23	2M	24.81 / 0.933	32.68 / 0.940	30.84 / 0.880	25.09 / 0.779	22.76 / 0.863	27.24 / 0.873	Specific
Multiple	SwinIR	ICCVW'21	1M	21.50 / 0.891	30.78 / 0.923	30.59 / 0.868	24.52 / 0.773	17.81 / 0.723	25.04 / 0.835	General
	MIRNet-v2	TPAMI'22	6M	24.03 / 0.927	33.89 / 0.954	30.97 / 0.881	26.30 / 0.799	21.52 / 0.815	27.34 / 0.875	General
	DGUNet	CVPR'22	17M	24.78 / 0.940	36.62 / 0.971	31.10 / 0.883	27.25 / 0.837	21.87 / 0.823	28.32 / 0.891	General
	Restormer	CVPR'22	26M	24.09 / 0.927	34.81 / 0.960	31.49 / 0.884	27.22 / 0.829	20.41 / 0.806	27.60 / 0.881	General
	NAFNet	ECCV'22	17M	25.23 / 0.939	35.56 / 0.967	31.02 / 0.883	26.53 / 0.808	20.49 / 0.809	27.76 / 0.881	General
	FSNet	TPAMI'23	13M	25.53 / 0.943	36.07 / 0.968	31.33 / 0.883	28.32 / 0.869	22.29 / 0.829	28.71 / 0.898	General
	MambaIR	ECCV'24	27M	25.81 / 0.944	36.55 / 0.971	31.41 / 0.884	28.61 / 0.875	22.49 / 0.832	28.97 / 0.901	General
All-in-One	DL	TPAMI'19	2M	20.54 / 0.826	21.96 / 0.762	23.09 / 0.745	19.86 / 0.672	19.83 / 0.712	21.05 / 0.743	parameterized image operator
	Transweather	CVPR'22	38M	21.32 / 0.885	29.43 / 0.905	29.00 / 0.841	25.12 / 0.757	21.21 / 0.792	25.22 / 0.836	weather type queries
	TAPE	ECCV'22	1M	22.16 / 0.861	29.67 / 0.904	30.18 / 0.855	24.47 / 0.763	18.97 / 0.621	25.09 / 0.801	task-agnostic prior
	AirNet	CVPR'22	9M	21.04 / 0.884	32.98 / 0.951	30.91 / 0.882	24.35 / 0.781	18.18 / 0.735	25.49 / 0.846	contrastive-based & degradation-guided
	IDR	CVPR'23	15M	25.24 / 0.943	35.63 / 0.965	31.60 / 0.887	27.87 / 0.846	21.34 / 0.826	28.34 / 0.893	ingredient-oriented learning
	PIP_Restormer	arXiv'23	27M	32.11 / 0.979	38.09 / 0.983	30.94 / 0.877	28.61 / 0.861	24.06 / 0.859	30.81 / 0.901	prompt-in-prompt learning
	PromptIR	NeurIPS'23	36M	26.54 / 0.949	36.37 / 0.970	31.47 / 0.886	28.71 / 0.881	22.68 / 0.832	29.15 / 0.904	prompt for AiOIR
	DASL_MPRNet	arXiv'23	15M	25.82 / 0.947	38.02 / 0.980	31.57 / 0.890	26.91 / 0.823	20.96 / 0.826	28.66 / 0.893	decomposition ascribed synergistic
	Gridformer	IJCV'23	34M	26.79 / 0.951	36.61 / 0.971	31.45 / 0.885	29.22 / 0.884	22.59 / 0.831	29.33 / 0.904	transformer with grid structure
	Art_PromptIR	ACM MM'24	36M	29.93 / 0.908	22.09 / 0.891	29.43 / 0.843	25.61 / 0.776	21.99 / 0.811	25.81 / 0.846	via multi-task collaboration
	DaAIR	arXiv'24	6M	31.97 / 0.980	36.28 / 0.975	31.07 / 0.878	29.51 / 0.890	22.38 / 0.825	30.24 / 0.910	efficient degradation-aware
	AnyIR	arXiv'24	6M	29.84 / 0.977	36.91 / 0.977	31.15 / 0.882	26.86 / 0.822	23.50 / 0.845	29.65 / 0.901	local-global gated intertwining
	MEASNet	arXiv'24	31M	31.05 / 0.980	38.32 / 0.982	31.40 / 0.888	29.41 / 0.890	23.00 / 0.845	30.64 / 0.917	multi-expert adaptive selection
	Hair	arXiv'24	29M	30.62 / 0.978	38.11 / 0.981	31.49 / 0.891	28.52 / 0.874	23.12 / 0.847	30.37 / 0.914	hypernetworks-based
	TUR_Transweather	AAAI'25	38M	29.68 / 0.966	33.09 / 0.952	30.40 / 0.869	26.63 / 0.815	23.02 / 0.838	28.56 / 0.888	a novel loss function
	AdaIR	ICLR'25	29M	30.53 / 0.978	38.02 / 0.981	31.35 / 0.889	28.12 / 0.858	23.00 / 0.845	30.20 / 0.910	frequency mining and modulation
	DA-RCOT	TPAMI'25	50M	30.96 / 0.975	37.87 / 0.980	31.23 / 0.888	28.68 / 0.872	23.25 / 0.836	30.40 / 0.911	as an optimal transport problem
	ABAIR	arXiv'24	41M	33.46 / 0.983	38.18 / 0.983	31.38 / 0.898	29.00 / 0.878	24.20 / 0.865	31.24 / 0.921	a three-phase approach
	MoCE-IR	CVPR'25	25M	30.48 / 0.974	38.04 / 0.982	31.34 / 0.887	30.05 / 0.899	23.00 / 0.852	30.58 / 0.919	mixture-of-complexity-experts framework
	DCPT_PromptIR	ICLR'25	35M	30.72 / 0.977	37.32 / 0.978	31.32 / 0.885	28.84 / 0.877	23.35 / 0.840	30.31 / 0.911	learn to classify degradation
	RamIR	APPL INTELL'25	22M	31.09 / 0.979	37.56 / 0.979	31.44 / 0.886	28.82 / 0.878	22.02 / 0.828	30.18 / 0.910	prompt-driven Mamba-based
	D3Net	arXiv'25	38M	32.57 / 0.965	38.35 / 0.973	31.73 / 0.860	32.70 / 0.851	26.49 / 0.857	32.36 / 0.901	cross-domain and dynamic decomposition
	Cat-AIR	arXiv'25	-	30.88 / 0.978	38.21 / 0.982	31.38 / 0.890	28.91 / 0.876	23.46 / 0.848	30.57 / 0.915	content and task-aware framework
	DSwinIR	arXiv'25	24M	30.09 / 0.975	37.77 / 0.982	31.34 / 0.885	29.17 / 0.879	22.64 / 0.843	30.19 / 0.913	deformable sliding window transformer
	CPL_PromptIR	arXiv'25	36M	30.82 / 0.978	38.20 / 0.983	31.41 / 0.887	28.72 / 0.874	23.65 / 0.855	30.55 / 0.915	contrastive prompt regularization
	AnyIR	arXiv'25	6M	31.41 / 0.980	38.51 / 0.983	31.37 / 0.891	28.85 / 0.883	23.11 / 0.856	30.65 / 0.919	local-global gated mechanism
	MIRAGE	arXiv'25	10M	31.45 / 0.980	38.92 / 0.985	31.41 / 0.892	28.10 / 0.858	23.59 / 0.858	30.68 / 0.914	within the SPD manifold space
	BaryIR	arXiv'25	-	31.12 / 0.976	38.05 / 0.981	31.43 / 0.891	29.30 / 0.888	23.38 / 0.852	30.66 / 0.918	in continuous barycenter space
	InstructIR-5D	ECCV'24	16M+17M	36.84 / 0.973	27.10 / 0.956	31.40 / 0.887	29.40 / 0.886	23.00 / 0.836	29.55 / 0.907	natural language prompts
	Perceive-IR	TIP'25	42M+86M	28.19 / 0.964	37.25 / 0.977	31.44 / 0.887	29.46 / 0.886	22.88 / 0.833	29.84 / 0.909	quality-aware degradation
	VLU-Net	CVPR'25	35M+88M	30.84 / 0.980	38.54 / 0.982	31.43 / 0.891	27.46 / 0.840	22.29 / 0.833	30.11 / 0.905	vision-language gradient descent-driven
	DFPIR	CVPR'25	31M+63M	31.64 / 0.979	37.62 / 0.978	31.29 / 0.889	28.82 / 0.873	23.62 / 0.852	30.60 / 0.914	degradation-aware feature perturbation
	CyclicPrompt	arXiv'25	30M+486M	33.02/0.983	37.03/0.989	31.33/0.941	29.42/0.925	21.79/0.837	30.52/0.935	cyclic prompt-driven universal framework

Performance Comparisons of AiOIR Models on All-Weather Datasets

Method	Snow	Rain+Fog	Raindrop	Average	Params
SwinIR	28.18/0.880	23.23/0.869	30.82/0.904	27.41/0.884	12M
MPRNet	28.66/0.869	30.25/0.914	30.99/0.916	29.30/0.900	16M
Restormer	29.37/0.881	29.22/0.907	31.21/0.919	29.93/0.902	26M
All-in-One	28.33/0.882	24.71/0.898	31.12/0.927	28.05/0.902	44M
Transweather	29.31/0.888	28.83/0.900	30.17/0.916	29.44/0.901	38M
AirNet	27.92/0.858	23.12/0.837	28.23/0.892	26.42/0.862	9M
WGWS-Net	28.91/0.856	29.28/0.922	32.01/0.925	30.07/0.901	6M
WeatherDiff	30.09/0.904	29.64/0.931	30.71/0.931	30.15/0.922	83M
TKMANet	30.24/0.902	29.92/0.917	30.99/0.927	30.38/0.915	29M
UtilityIR	29.47/0.879	31.16/0.927	32.01/0.925	30.88/0.910	26M
AWRCP	31.92/0.934	31.39/0.933	31.93/0.931	31.75/0.933	-
Histoformer	32.16/0.926	32.08/0.939	33.06/0.944	32.43/0.936	17M
LoRA-IR	32.28/0.930	32.62/0.945	33.39/0.949	32.76/0.941	-
T3-DiffWeather	32.37/0.936	31.99/0.937	32.66/0.941	32.34/0.938	69M+25M
MWFormer	30.92/0.908	30.27/0.912	31.91/0.927	31.03/0.916	170M
TUR_Transweather	30.62/0.909	29.75/0.907	31.61/0.933	30.66/0.916	38M
CyclicPrompt	32.16/0.927	32.81/0.937	32.57/0.945	32.51/0.936	30M+486M
DSwinIR	32.58/0.931	32.76/0.950	32.88/0.947	32.74/0.943	24M
DA2Diff	31.42/0.916	31.58/0.939	33.01/0.945	31.67/0.933	-
HOGformer	32.41/0.930	32.89/0.946	32.72/0.945	32.67/0.940	17M
CPL_PromptIR	32.27/0.928	32.16/0.942	32.73/0.943	32.39/0.938	36M
MODEM	32.52/0.929	33.10/0.941	33.01/0.943	32.87/0.938	20M

Method	Haze	Rain	Snow	Average	Params
the WeatherStream Dataset
NAFNet	22.20/0.803	23.01/0.803	22.11/0.826	22.44/0.811	17M
GRL	22.88/0.802	23.75/0.805	22.59/0.829	23.07/0.812	3M
Restormer	22.90/0.803	23.67/0.804	22.51/0.828	22.86/0.812	26M
MPRNet	21.73/0.763	21.50/0.791	20.74/0.801	21.32/0.785	16M
Transweather	22.55/0.774	22.21/0.772	21.79/0.792	22.18/0.779	38M
AirNet	21.56/0.770	22.52/0.797	21.44/0.812	21.84/0.793	9M
TKMANet	22.38/0.805	23.22/0.795	22.25/0.827	22.62/0.809	29M
WGWS-Net	22.78/0.800	23.80/0.807	22.72/0.831	23.10/0.813	6M
the Real-World Dataset
TKMANet	20.10/0.85	37.32/0.97	29.37/0.88	28.93/0.90	29M
TransWeather	17.33/0.82	33.64/0.93	26.92/0.86	26.71/0.86	38M
TUR_Transweather	20.38/0.88	39.78/0.98	29.72/0.91	29.96/0.92	38M
WGWS-Net	29.46/0.85	38.94/0.98	33.61/0.93	34.01/0.92	6M
DSwinIR	30.14/0.89	40.60/0.98	33.80/0.93	34.85/0.93	24M

Performance Comparisons of AiOIR Models on CDD-11 Datasets

Type	Method	Venue & Year	PSNR	SSIM	Params
One-to-One	MPRNet	CVPR'21	25.47	0.856	16M
One-to-One	MIRNetv2	TPAMI'22	25.37	0.854	6M
One-to-One	Restormer	CVPR'22	26.99	0.865	26M
One-to-One	DGUNet	CVPR'22	25.33	0.844	18M
One-to-One	NAFNet	ECCV'22	26.22	0.796	17M
One-to-One	SRUDC	ICCV'23	27.64	0.860	7M
One-to-One	Fourmer	ICML'23	23.44	0.789	6M
One-to-One	OKNet	AAAI'24	26.33	0.861	6M
One-to-Many	AirNet	CVPR'22	23.75	0.814	9M
One-to-Many	TransWeather	CVPR'22	23.13	0.804	38M
One-to-Many	WeatherDiff	TPAMI'23	24.09	0.799	83M
One-to-Many	PromptIR	NeurIPS'23	25.90	0.850	36M
One-to-Many	WGWS-Net	CVPR'23	26.96	0.861	6M
One-to-Many	HAIR	arXiv'24	27.85	0.866	29M
One-to-Composite	OneRestore	ECCV'24	28.47	0.878	6M
One-to-Composite	AllRestorer	arXiv'24	33.72	0.944	12M+88M
One-to-Composite	DA-CLIP_NAFNet	ICLR'24	26.56	0.860	86M+125M
One-to-Composite	MoCE-IR-S	CVPR'25	29.05	0.881	11M
One-to-Composite	DCPT_NAFNet	ICLR'25	30.66	0.891	68M
One-to-Composite	VL-UR	arXiv'25	28.76	0.879	-
One-to-Composite	MIRAGE	arXiv'25	29.33	0.887	10M
Step-by-Step	CoR_HAIR	arXiv'24	28.33	0.869	30M
Step-by-Step	CoR_OneRestore	arXiv'24	28.84	0.879	8M

Performance Comparisons of AiOIR Models on FoundIR's Real-World Datasets

Methods	Blur	Noise	JPEG	Haze	Rain	Raindrop	Lowlight	B+N	B+J	N+J	R+H	L+H	L+R	L+B	L+N	L+J	L+B+N	L+B+J	L+N+J	B+N+J	Average
Input	20.61/0.6544	37.30/0.9329	32.83/0.9530	13.47/0.6394	23.45/0.7791	20.76/0.6792	6.99/0.1802	22.85/0.7559	22.87/0.7450	38.45/0.9747	12.16/0.4774	9.94/0.3250	30.00/0.8935	10.55/0.4328	8.07/0.2535	8.50/0.3261	9.70/0.4079	9.01/0.4555	8.65/0.4984	22.44/0.7009	18.40/0.6033
DGUNet	21.86/0.7334	36.69/0.9494	29.80/0.8906	18.58/0.6762	25.47/0.8245	24.83/0.7924	16.16/0.6494	22.90/0.7633	22.86/0.7358	35.28/0.9564	18.79/0.4981	13.20/0.4182	30.66/0.9097	11.54/0.4922	12.56/0.5349	12.17/0.5433	10.60/0.4608	9.57/0.4897	9.64/0.5456	22.43/0.6945	20.27/0.6779
Restormer	21.81/0.7268	34.80/0.9311	29.08/0.8742	13.53/0.5316	24.70/0.7773	23.87/0.7395	8.64/0.3845	22.83/0.7474	22.76/0.7266	34.09/0.9412	12.88/0.4096	10.84/0.3110	29.72/0.8757	10.90/0.4487	8.40/0.3255	10.08/0.4492	9.74/0.4110	9.30/0.4647	10.30/0.5761	22.28/0.6836	18.52/0.6167
DiffIR	21.88/0.7346	37.69/0.9508	32.94/0.9313	19.06/0.7801	25.77/0.8249	25.34/0.8183	16.90/0.7311	22.90/0.7502	22.91/0.7373	38.97/0.9732	19.63/0.6275	18.78/0.7435	30.87/0.8971	22.10/0.7203	14.81/0.4651	25.66/0.8761	22.00/0.6862	21.68/0.7303	31.36/0.9613	22.48/0.6958	24.68/0.7817
IR-SDE	19.08/0.6395	23.67/0.8610	21.91/0.7738	13.67/0.5080	20.05/0.6541	20.61/0.6789	6.93/0.1578	19.77/0.6610	18.82/0.6118	22.35/0.8187	12.62/0.3905	9.64/0.2664	25.49/0.7651	10.21/0.3399	7.95/0.2049	8.44/0.2649	9.29/0.3274	8.63/0.3729	8.29/0.4027	18.64/0.5838	15.30/0.5141
RDDM	16.37/0.7183	14.94/0.8519	17.95/0.8419	11.12/0.6435	15.55/0.7118	15.47/0.6528	13.16/0.7027	15.82/0.7156	16.75/0.6822	18.23/0.9066	10.52/0.4568	13.87/0.3972	12.53/0.5537	17.26/0.6471	13.39/0.6025	14.09/0.5931	17.34/0.6457	15.98/0.6822	16.88/0.8222	17.76/0.6679	15.24/0.6747
X-Restormer	21.88/0.7325	35.86/0.9412	28.58/0.8646	16.47/0.6257	25.70/0.8076	26.11/0.8368	16.02/0.6404	22.90/0.7544	22.85/0.7321	33.83/0.9405	15.17/0.4354	14.75/0.4416	30.93/0.9026	19.38/0.6605	9.75/0.3866	18.66/0.7205	22.00/0.6841	13.63/0.5738	16.40/0.7810	22.41/0.6894	21.66/0.7075
All-in-One models
AirNet	18.07/0.5950	19.61/0.7588	19.42/0.5495	14.13/0.3792	17.61/0.4446	16.97/0.3233	6.60/0.1153	18.41/0.6054	19.22/0.6108	17.81/0.5239	13.53/0.2376	8.39/0.1452	22.41/0.6397	9.84/0.3293	7.75/0.2162	8.02/0.2210	8.76/0.2676	7.99/0.3122	7.83/0.3065	18.32/0.5282	14.03/0.4054
TransWeather	21.34/0.7103	30.12/0.8945	23.52/0.7296	17.72/0.5635	23.49/0.6886	22.94/0.6814	14.95/0.6295	22.19/0.7363	22.14/0.7105	25.59/0.8377	18.43/0.4245	15.99/0.4285	28.29/0.8663	21.35/0.6764	11.56/0.5181	19.16/0.6528	20.83/0.6607	19.64/0.6918	21.41/0.8068	21.64/0.6577	21.11/0.6782
IDR	17.75/0.6139	21.51/0.7896	17.96/0.5207	12.60/0.3581	16.37/0.4363	16.21/0.3422	6.96/0.1837	18.05/0.6243	18.21/0.6063	16.05/0.4826	11.40/0.2410	9.77/0.2377	23.42/0.7939	10.34/0.3976	7.92/0.2631	8.32/0.2696	9.51/0.3652	8.89/0.4170	8.34/0.3500	17.16/0.5209	13.83/0.4406
PromptIR	21.91/0.7339	36.57/0.9478	29.63/0.8842	15.36/0.4982	27.59/0.8411	25.83/0.8327	16.33/0.6353	22.93/0.7587	22.90/0.7360	35.08/0.9524	16.61/0.4985	15.36/0.4982	31.03/0.9039	20.29/0.6723	10.83/0.4499	21.52/0.7671	22.63/0.6924	12.40/0.5597	22.71/0.8616	22.47/0.6942	22.49/0.7209
DiffUIR	25.31/0.7979	34.48/0.9622	30.09/0.9390	19.97/0.8193	30.17/0.9350	26.98/0.8908	14.02/0.7101	24.44/0.8039	21.36/0.6915	31.96/0.9782	20.24/0.7268	19.31/0.7745	32.35/0.9255	18.97/0.6939	13.88/0.6262	19.98/0.8706	18.89/0.6705	18.64/0.6751	20.66/0.9338	23.72/0.7861	23.27/0.8105
DA-CLIP	20.92/0.6954	29.45/0.9027	25.77/0.7816	15.91/0.5399	23.04/0.6849	20.86/0.6490	17.34/0.7412	22.15/0.7293	21.36/0.6940	26.03/0.8602	13.97/0.3563	12.62/0.3220	21.58/0.7246	16.17/0.6241	15.70/0.6365	15.86/0.6048	15.30/0.6202	12.46/0.5774	15.34/0.7068	21.19/0.6589	19.15/0.6554
Real-ESRGAN	25.20/0.7868	34.46/0.9585	27.62/0.9108	22.07/0.8380	28.95/0.9226	28.94/0.9115	19.26/0.8709	23.48/0.7728	20.41/0.6562	29.71/0.9566	20.40/0.7153	21.79/0.8084	32.16/0.9116	21.95/0.7254	17.49/0.7358	22.89/0.8704	21.43/0.6612	19.49/0.6582	26.11/0.9496	21.40/0.7197	24.26/0.8173
SUPIR	20.92/0.6649	34.11/0.9035	24.52/0.7189	-	-	-	-	21.69/0.6828	21.34/0.6293	26.97/0.8003	-	-	-	-	-	-	-	-	-	20.18/0.5768	-
InstructIR	20.15/0.6801	38.58/0.9628	33.44/0.9378	16.85/0.7555	30.18/0.8997	21.05/0.6828	20.04/0.8542	21.70/0.7185	21.39/0.6814	39.90/0.9770	13.49/0.5535	13.52/0.4983	29.87/0.8866	17.43/0.6676	16.37/0.4625	18.06/0.7787	12.78/0.5392	17.39/0.7092	19.13/0.9105	22.42/0.6980	22.18/0.7426
AutoDIR	20.31/0.6946	36.84/0.9221	32.99/0.9280	15.23/0.6264	25.69/0.7711	20.82/0.6687	21.90/0.8288	21.90/0.7293	22.03/0.7088	37.55/0.9616	14.90/0.4213	14.50/0.4456	27.15/0.8576	19.14/0.6570	17.49/0.6900	16.14/0.6375	18.91/0.6499	16.91/0.6761	18.78/0.8122	22.37/0.6876	22.07/0.7187
FoundIR	25.93/0.7914	38.98/0.9647	34.03/0.9427	22.19/0.8492	34.29/0.9434	29.74/0.9160	18.98/0.8576	23.87/0.7737	29.58/0.8544	40.43/0.9795	21.80/0.7582	22.82/0.8048	33.96/0.9330	24.15/0.7808	18.95/0.7454	29.08/0.9098	23.56/0.7550	22.55/0.8181	33.46/0.9636	27.98/0.7452	27.81/0.8529

Star History

Citations

If our survey helps your research or work, please consider citing our paper. The following are BibTeX references:

@article{jiang2025survey,
  title={A survey on all-in-one image restoration: Taxonomy, evaluation and future trends},
  author={Jiang, Junjun and Zuo, Zengyuan and Wu, Gang and Jiang, Kui and Liu, Xianming},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={47},
  number={12},
  pages={11892--11911},
  year={2025}
}

Contributing

📮📮📮 If you want to add your model in our leaderboards, please feel free to fork and update your work in the table. You can also email 3565741165@qq.com. We will response to your request as soon as possible!

all-in-one-image-restoration

image-restoration

survey

Significant stargazers

Ziyue Lin

3 followers · starred Aug 2025

Similar repos

ChaofWang/Awesome-Super-Resolution

Collect super-resolution related papers, data, repositories

3,099

ChunmingHe/awesome-diffusion-models-in-low-level-vision

A Repository for Diffusion-Model-related Papers in Low-level Vision

558

lixinustc/Awesome-diffusion-model-for-image-processing

one summary of diffusion-based image processing, including restoration, enhancement, coding,…

955

DarrenPan/Awesome-ICCV2023-Low-Level-Vision

A Collection of Papers and Codes in ICCV2023/2021 about low level vision

194

krantbrity/Single-Image-Reflection-Removal-Papers-and-Code-Collection

ChunmingHe/awesome-multimodal-large-language-models-in-low-level-vision

DarrenPan/Awesome-CVPR2024-Low-Level-Vision

A Collection of Papers and Codes in CVPR2023/2022 about low level vision

658

AlonzoLeeeooo/awesome-image-inpainting-studies

A collection of awesome image inpainting studies.

396

Harbinzzy/All-in-One-Image-Restoration-Survey

[IEEE TPAMI 2025] A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

603

219 commits

updated Sep 27, 2026

See the code

README

A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

Junjun Jiang, Zengyuan Zuo,Gang Wu, Kui Jiang and Xianming Liu

AIIA Lab, Harbin Institute of Technology.

📚 Overview

Awesome-AiOIR-Methods
2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026
Awesome-AiOIR-Benchmarks
Three Challenging Datasets | Five Challenging Datasets | All-Weather | Real-World Weather-Related | CDD-11 | FoundIR's Datasets
Citations | Contributing

📢 News

✅ Our comprehensive survey paper on All-in-One Image Restoration has been released and is actively maintained.
📝 Submitted on 19 Oct 2024 (v1), last revised on 12 Jun 2025 (v2) with major updates and reductions.
We will continue to reflect the latest advancements in this evolving field. (IEEE TPAMI 25)

📖 All-in-one Image Restoration Paper List

2026

Paper	Avenue	Link	Code
Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration _{Xinyao Wang, Lijun He, Zhihan Ren, Fan Li}	arXiv	Paper
ImIR: Image-Instruction Tuning for All-in-One Image Restoration _{Süleyman Aslan, Görkay Aydemir, Mısra Yavuz, Yunus Bilge Kurt, Nasrin Rahimi, Ahmet Rasim Emirdağı, Burak Can Biner, M. Akın Yılmaz}	ACCV 2026	Paper
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration _{Hu Gao, Lizhuang Ma, Yulong Chen}	arXiv	Paper
UniH³: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration _{Zhiwen Yang, Jiayin Li, Chengyu Liu, Hui Zhang, Bingzheng Wei, Yan Xu}	ECCV 2026	Paper	Code
MARR: Decoupling Policy, Execution, and Calibration for All-in-One Medical Image Restoration _{Haobin Chen, Ao Chang, Heqin Zhu, Rundong Wang, Ting Liu, Shaohua Kevin Zhou}	arXiv	Paper	Code
Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network _{Zheke Jin, Yuning Cui, Tianle Jin, Alois Knoll, Hu Cao}	arXiv	Paper
DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration _{Zhaokun He, Kangbiao Shi, Axi Niu, Jian Jin, Peng Wu, Wei Dong, Qingsen Yan}	arXiv	Paper
Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance _{Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng}	ACM MM 2026	Paper
Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal _{Wanshu Fan, Yunzhe Zhang, Yue Shen, Liyan Wang, Jing Qin, Kin-Man Lam, Cong Wang, Jinshan Pan}	TIP 2026	Paper	Code
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration _{Zihao He, Yunfeng Wu, Xinchao Wang, Songhua Liu}	ICML 2026	Paper
SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning _{Shengkai Hu, Jie Shao, Jiaqi Ma, Xu Zhang, Keying Wu, Qilu Zhu, Beihang Song, Jun Wan}	arXiv	Paper
MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration _{Yongcong Wang, Pu Wang, Hingchin Chen, Runci Bai, Yucheng Xin, Chen Wu, Chengchao Shen, Guangwei Gao, Siyuan Yao, Pengwen Dai, Zhuoran Zheng}	arXiv	Paper
What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration _{Cencen Liu, Wen Yin, Dongyang Zhang, Dongmin Li, Shan Zhao, Bing Su, Tao He, Jielei Wang, Guoming Lu}	arXiv	Paper
CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration _{Zaiyan Zhang, Qiangqiang Yuan, Jie Li, Ziyang Lihe, Yu Wan, Yuzeng Chen, Xin Su, Liangpei Zhang}	ISPRS 2026	Paper	Code
Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents _{Hu Gao, Yulong Chen, Lizhuang Ma}	arXiv	Paper
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback _{Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun Fu}	CVPR 2026
IAMAgent: Toward an Interactive and Adaptive Multi-Agent System for Image Restoration _{Yanyan Wei, Yilin Zhang, Zhao Zhang, Huan Zheng, Jiahuan Ren, Xiaogang Xu, Meng Wang, Zenglin Shi}	TIP 2026	Paper
QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration _{Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian, Zhen Wu, Guangwen Peng, Zhiyuan Li, Ding Ding, Dian Shen, Fang Dong}	ACM MM 2026	Paper	Code
Virtual Consistency Model for All-in-one Image Restoration _{Jiawei Wu, Luwei Tu, Zhe Wang, Zhi Jin, Kaihao Zhang, Wenqi Ren, Xiaochun Cao}	TIP 2026	Paper
Transformer-Inspired Convolutional Network for Image Restoration _{Yuning Cui, Mingyu Liu, Wenqi Ren, Boxin Shi, Alois Knoll}	TCSVT 2026	Paper
Prompt-In-Prompt Learning for Universal Image Restoration _{Zilong Li, Yiming Lei, Chenglong Ma, Junping Zhang, Hongming Shan}	PR 2026	Paper	Code
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration _{Zihao He, Yunfeng Wu, Xinchao Wang, Songhua Liu}	ICML 2026	Paper
Hierarchical Physical-Chain Decoupling With Geo-Semantic MoLoRA for All-in-One Multimodal Remote Sensing Image Restoration _{Zhentao Zou, Jichu Zhan, Yue Zhou, Ran Ding, Jia Fu, Chaofeng Chen, Jianxin Xing, Xiaogang Yu, Xue Jiang}	TGRS 2026	Paper	Code
Learning Dual Transformers for All-in-One Image Restoration From a Frequency Perspective _{Jie Chu, Tong Su, Pei Liu, Yunpeng Wu, Le Zhang, Zenglin Shi, Meng Wang}	TNNLS 2026	Paper
Learning Adaptive Dynamical Features via Multi-τ Liquid-Mamba for All-in-one Image Restoration _{Hu Gao, Changshuo Wang, Yulong Chen, Lizhuang Ma}	arXiv	Paper
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration _{Yanjie Tu, Qingsen Yan, Axi Niu, Tao Hu, Haokui Zhang, Jiantao Zhou}	arXiv	Paper	Code
Universal Image Restoration via Internalized Chain-of-Thought Reasoning _{Yu Guo, Zhengru Fang, Shengfeng He, Senkang Hu, Yihang Tao, Phone Lin, Yuguang Fang}	arXiv	Paper	Code
DDTNet: Degradation Disentanglement and Transfer Network for Test-Time All-in-One De-weathering Adaptation _{Kuan-Hung Lin, Fu-Jen Tsai, Yan-Tsung Peng, Min-Hung Chen, Chia-Wen Lin, Yen-Yu Lin}	arXiv	Paper
Hierarchical Physical-Chain Decoupling With Geo-Semantic MoLoRA for All-in-One Multimodal Remote Sensing Image Restoration _{Zhentao Zou, Jichu Zhan, Yue Zhou, Ran Ding, Jia Fu, Chaofeng Chen, Jianxin Xing, Xiaogang Yu, Xue Jiang}	TGRS 2026	Paper	Code
Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration _{Ni Tang, Shenghao Nie, Xiaotong Luo, Yuan Xie, Yanyun Qu}	CVPR 2026	Paper
Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank _{Chenxu Wang, Kai Zhang, Jian Yang}	CVPR 2026	Paper	Code
DiTTo: Scalable Order-aware All-in-One Image Restoration Agent _{Seungho Choi, Jihyong Oh}	arXiv	Paper	Code
OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization _{Feng Zhu, Shuyang Xie, Yihan Zeng, Ming Liu, Wangmeng Zuo}	arXiv	Paper	Code
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration _{Xinghua Huang, Zhixiong Yang, Chen Wu, Shengxi Li, Shuaifeng Zhi, Yue Zhang, Qibin Hou, Xin Deng, Jingyuan Xia}	arXiv	Paper
Expandable, Compressible, Mineable: Open-World Thermal Image Restoration _{Pu Li, Huafeng Li, Yafei Zhang, Wen Wang, Neng Dong, Jie Wen}	ICML 2026	Paper	Code
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts _{Eunho Lee, Rei Kawakami, Youngbae Hwang}	arXiv	Paper
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization _{Ao Li, Xiaoning Liu, Sheng Li, Yapeng Du, Zhen Long, Lei Luo, Le Zhang, Ce Zhu}	TMM 2026	Paper	Code
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration _{Haisen He, Xiangyu Zou, SongLin Dong, Heng Li, Yihong Gong, Zhiheng Ma}	arXiv	Paper
PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow _{Wei Dong, Han Zhou, Terry Ji, Guanhua Zhao, Shahab Asoodeh, Yulun Zhang, Guangtao Zhai, Jun Chen, Xiaohong Liu}	arXiv	Paper	Code
UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement _{Weiqi Li, Xuanyu Zhang, Bin Chen, Jingfen Xie, Yan Wang, Kexin Zhang, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao}	arXiv	Paper	Code
Residual Diffusion Bridge Model for Image Restoration _{Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du}	CVPR 2026	Paper	Code
Hybrid Agents for Image Restoration _{Bingchen Li, Xin Li, Yiting Lu, Zhibo Chen}	CVPR 2026	Paper
UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration _{Zihan Cheng, Liangtai Zhou, Dian Chen, Ni Tang, Xiaotong Luo, Yanyun Qu}	CVPR 2026	Paper
FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration _{Jingren Liu, Shuning Xu, Qirui Yang, Yun Wang, Xiangyu Chen, Zhong Ji}	CVPR 2026	Paper	Code
FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model _{Xiang Chen, Jinshan Pan, Jiangxin Dong, Jian Yang, Jinhui Tang}	CVPR 2026	Paper	Code
Degradation-Aware Adaptive Context Gating for Unified Image Restoration _{Lei He, Jielei Chu, Fengmao Lv, Weide Liu, Tianrui Li, Jun Cheng, Yuming Fang}	arXiv	Paper	Code
Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement _{Pu Li, Huafeng Li, Yafei Zhang, Yu Liu, Wen Wang}	CVPR 2026	Paper	Code
LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results _{Xiang Chen, Hao Li, Jiangxin Dong, Jinshan Pan, et al.}	CVPR Workshops 2026	Paper
CDIR: LoRA-Inspired Attention for Efficient Composite Degradation Image Restoration _{Yuning Cui, Wenqi Ren, Boxin Shi, Jianhou Gan, Alois Knoll}	TIP 2026	Paper
A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting _{Yongchuan Cui, Peng Liu}	arXiv	Paper	Code
RIRF: Reasoning Image Restoration Framework _{Wending Yan, Rongkai Zhang, Kaihua Tang, Yu Cheng, Qiankun Liu}	arXiv	Paper
WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression _{Weikai Qu, Sijun Liang, Cheng Pan, Zikuan Yang, Guanchi Zhou, Xianjun Fu, Bo Liu, Changmiao Wang, Ahmed Elazab}	TAI 2026	Paper	Code
Task-Guided Prompting for Unified Remote Sensing Image Restoration _{Wenli Huang, Yang Wu, Xiaomeng Xin, Zhihong Liu, Jinjun Wang, Ye Deng}	TGRS 2026	Paper	Code
Your Pre-trained Diffusion Model Secretly Knows Restoration _{Sudarshan Rajagopalan, Vishal M. Patel}	arXiv	Paper	Code
A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting _{Yongchuan Cui, Peng Liu}	arXiv	Paper	Code
TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration _{Yisheng Zhang, Guoli Jia, Haote Hu, Shanxu Zhao, Kaikai Zhao, Long Sun, Xinwei Long, Kai Tian, Che Jiang, Zhaoxiang Liu, Kai Wang, Shiguo Lian, Kaiyan Zhang, Bowen Zhou}	arXiv	Paper
Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration _{I-Hsiang Chen, Isma Hadji, Enrique Sanchez, Adrian Bulat, Sy-Yen Kuo, Radu Timofte, Georgios Tzimiropoulos, Brais Martinez}	CVPR 2026	Paper	Code
Focal Modulation for Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	IJCV 2026	Paper	Code
StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion _{Yuning Cui, Syed Waqas Zamir, Ming-Hsuan Yang, Alois Knoll, Fahad Shahbaz Khan, Salman Khan}	TPAMI 2026	Paper	Code
Visual-in-Visual: A Unified and Efficient Baseline for Image Restoration _{Yuning Cui, Wenqi Ren, Boxin Shi, Alois Knoll}	TPAMI 2026	Paper
M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts _{Shiwei Wang, Yongzhen Wang, Bingwen Hu, Liyan Zhang, Xiao-Ping Zhang, Mingqiang Wei}	arXiv	Paper	Code
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration _{Debabrata Mandal, Soumitri Chattopadhyay, Yujie Wang, Marc Niethammer, Praneeth Chakravarthula}	arXiv	Paper
SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration _{Peng Shurui, Xin Lin, Shi Luo, Jincen Ou, Dizhe Zhang, Lu Qi, Truong Nguyen, Chao Ren}	arXiv	Paper
All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network _{Bingnan Wang, Bin Qin, Jiangmeng Li, Fanjiang Xu, Fuchun Sun, Hui Xiong}	TIP 2026	Paper
Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration _{Guanglu Dong, Chunlei Li, Chao Ren, Jingliang Hu, Yilei Shi, Xiao Xiang Zhu, Lichao Mou}	ICLR 2026	Paper	Code
MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration _{Lingshun Kong, Jiawei Zhang, Zhengpeng Duan, Xiaohe Wu, Yueqi Yang, Xiaotao Wang, Dongqing Zou, Lei Lei, Jinshan Pan}	arXiv	Paper	Code
Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration _{Xiaole Tang, Xiaoyi He, Jiayi Xu, Xiang Gu, Jian Sun}	TPAMI 2026	Paper	Code
PromptHSI: Universal Hyperspectral Image Restoration Framework for Composite Degradation _{Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin, Yi-Ching Cheng, Wo-Ting Liao, Chih-Chung Hsu, Fu-En Yang, Yu-Chiang Frank Wang}	TGRS 2026	Paper	Code
HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression _{Xiangming Wang, Benteng Sun, Yungeng Liu, Haijin Zeng, Yongyong Chen, Jingyong Su, Jie Liu}	arXiv	Paper	Code
Bridging Degradation Discrimination and Generation for Universal Image Restoration _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Yanye Lu}	ICLR 2026	Paper	Code
Vision-Language Controlled Deep Unfolding for Joint Medical Image Restoration and Segmentation _{Ping Chen, Zicheng Huang, Xiangming Wang, Yungeng Liu, Bingyu Liang, Haijin Zeng, Yongyong Chen}	arXiv	Paper	Code
DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library _{Shihong Liu, Kun Zuo, Hanguang Xiao}	ICASSP 2026	Paper
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration _{Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin}	arXiv	Paper
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration _{Yanjie Tu, Qingsen Yan, Axi Niu, Jiacong Tang}	arXiv	Paper	Code
From Physical Degradation Models to Task-Aware All-in-One Image Restoration _{Hu Gao, Xiaoning Lei, Xichen Xu, Xingjian Wang, Lizhuang Ma}	arXiv	Paper
Edit2Restore: Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models _{M. Akın Yılmaz, Ahmet Bilican, Burak Can Biner, A. Murat Tekalp}	arXiv	Paper	Code
UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing _{Zengyuan Zuo, Junjun Jiang, Gang Wu, Xianming Liu}	arXiv	Paper	Code
ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration _{Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang}	AAAI 2026	Paper	Code
Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration _{Jiawei Wu, Zhifei Yang, Zhe Wang, Zhi Jin}	AAAI 2026	Paper	Code
EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion _{Tong Chen, Xinyu Ma, Long Bai, Wenyang Wang, Yue Sun, Luping Zhou}	AAAI 2026	Paper	Code

2025

Paper	Avenue	Link	Code
Enhancing Image Restoration Transformer via Adaptive Translation Equivariance _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Hangzhou He, Yanye Lu}	ICCV 2025	Paper
Degradation-Aware Prompted Transformer for Unified Medical Image Restoration _{Jinbao Wei, Gang Yang, Zhijie Wang, Shimin Tao, Aiping Liu, Xun Chen}	TIP 2025	Paper	Code
SimpleCall: A Lightweight Image Restoration Agent in Label-Free Environments with MLLM Perceptual Feedback _{Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun Fu}	arXiv	Paper
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration _{Binfeng Wang, Di Wang, Haonan Guo, Ying Fu, Jing Zhang}	arXiv	Paper	Code
TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration _{Zhiwen Yang, Jiaju Zhang, Yang Yi, Jian Liang, Bingzheng Wei, Yan Xu}	MICCAI 2025	Paper	Code
DSwinIR: Rethinking Window-Based Attention for Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TPAMI 2025	Paper	Code
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration	TIP 2025	Paper
ClusIR: Towards Cluster-Guided All-in-One Image Restoration _{Shengkai Hu, Jiaqi Ma, Jun Wan, Wenwen Min, Yongcheng Jing, Lefei Zhang, Dacheng Tao}	arXiv	Paper
Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration _{Wenlong Jiao, Heyang Lee, Ping Wang, Pengfei Zhu, Qinghua Hu, Dongwei Ren}	arXiv	Paper	Code
EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulation _{Jiaqi Ma, Shengkai Hu, Jun Wan, Jiaxing Huang, Lefei Zhang, Salman Khan}	arXiv	Paper
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TPAMI 2025	Paper	Code
Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation _{Hu Gao, Xiaoning Lei, Ying Zhang, Xichen Xu, Guannan Jiang, Lizhuang Ma}	arXiv	Paper
Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution _{Hu Gao, Xiaoning Lei, Xichen Xu, Depeng Dang, Lizhuang Ma}	arXiv	Paper
MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration _{Tao Wang, Peiwen Xia, Bo Li, Peng-Tao Jiang, Zhe Kong, Kaihao Zhang, Tong Lu, Wenhan Luo}	ICCV 2025	Paper
Bio-Inspired Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	NeurIPS 2025	Paper	Code
A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks _{Xiaoxuan Gong, Jie Ma}	NeurIPS 2025	Paper
Residual Diffusion Bridge Model for Image Restoration _{Hebaixu Wang, Jing Zhang, Haoyang Chen, Haonan Guo, Di Wang, Jiayi Ma, Bo Du}	arXiv	Paper	Code
UniUIR: Considering Underwater Image Restoration as An All-in-One Learner _{Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang, Bo Du}	TIP 2025	Paper	Code
Frequency-Prompted Image Restoration to Enhance Perception in Intelligent Transportation Systems _{Yuning Cui, Mingyu Liu, Xiongfei Su, Alois Knoll}	TITS 2025	Paper
Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration _{Thomas Katraouras, Dimitrios Rafailidis}	WI-IAT 2025	Paper	Code
Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement _{Yidi Liu, Xueyang Fu, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Zheng-Jun Zha}	NeurIPS 2025	Paper	Code
UHD-Processor: Unified UHD Image Restoration with Progressive Frequency Learning and Degradation-aware Prompts _{Yidi Liu, Xueyang Fu, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Zheng-Jun Zha}	CVPR 2025	Paper	Code
Universal Image Restoration Pre-training via Masked Degradation Classification _{JiaKui Hu, Zhengjian Yao, Lujia Jin, Yinghao Chen, Yanye Lu}	arXiv	Paper	Code
Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation _{Vijay M. Galshetwar, Praful Hambarde, Prashant W. Patil, Akshay Dudhane, Sachin Chaudhary, Santosh Kumar Vipparathi, Subrahmanyam Murala}	arXiv	Paper	Code
PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration _{Zhe Dong, Yuzhe Sun, Haochen Jiang, Tianzhu Liu, Yanfeng Gu}	arXiv	Paper	Code
Orochi: Versatile Biomedical Image Processor _{Gaole Dai, Chenghao Zhou, Yu Zhou, Rongyu Zhang, Yuan Zhang, Chengkai Hou, Tiejun Huang, Jianxu Chen, Shanghang Zhang}	NeurIPS 2025	Paper
Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding _{S M A Sharif, Abdur Rehman, Fayaz Ali Dharejo, Radu Timofte, Rizwan Ali Naqvi}	arXiv	Paper	Code
JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration _{Yunlong Lin, Zixu Lin, Haoyu Chen, Panwang Pan, Chenxin Li, Sixiang Chen, Kairun Wen, Yeying Jin, Wenbo Li, Xinghao Ding}	CVPR 2025	Paper	Code
RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration _{Zilong Zhang, Chujie Qin, Chunle Guo, Yong Zhang, Chao Xue, Ming-Ming Cheng, Chongyi Li}	arXiv	Paper	Code
WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration _{Qiyuan Guan, Qianfeng Yang, Xiang Chen, Tianyu Song, Guiyue Jin, Jiyu Jin}	ACMMM 2025	Paper	Code
Modumer: Modulating Transformer for Image Restoration _{Yuning Cui, Mingyu Liu, Wenqi Ren, Alois Knoll}	TNNLS 2025	Paper
TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal _{Hanting Wang, Shengpeng Ji, Shulei Wang, Hai Huang, Xiao Jin, Qifei Zhang, Tao Jin}	arXiv	Paper
Diffusion Once and Done: Degradation‑Aware LoRA for Efficient All‑in‑One Image Restoration _{Ni Tang, Xiaotong Luo, Zihan Cheng, Liangtai Zhou, Dongxiao Zhang, Yanyun Qu}	arXiv	Paper
Exploiting Diffusion Prior for Task-driven Image Restoration _{Jaeha Kim, Junghun Oh, Kyoung Mu Lee}	ICCV 2025	Paper	Code
Robust Adverse Weather Removal via Spectral-based Spatial Grouping _{Yuhwan Jeong, Yunseo Yang, Youngjo Yoon, Kuk-Jin Yoon}	ICCV 2025	Paper	Code
All-in-One Medical Image Restoration with Latent Diffusion-Enhanced Vector-Quantized Codebook Prior _{Haowei Chen, Zhiwen Yang, Haotian Hou, Hui Zhang, Bingzheng Wei, Gang Zhou, Yan Xu}	MICCAI 2025	Paper
Exploring Scalable Unified Modeling for General Low-Level Vision _{Xiangyu Chen, Kaiwen Zhu, Yuandong Pu, Shuo Cao, Xiaohui Li, Wenlong Zhang, Yihao Liu, Yu Qiao, Jiantao Zhou, Chao Dong}	arXiv	Paper
Exploring the Potential of Pooling Techniques for Universal Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	TIP 2025	Paper	Code
4KAgent: Agentic Any Image to 4K Super-Resolution _{Yushen Zuo, Qi Zheng, Mingyang Wu, Xinrui Jiang, Renjie Li, Jian Wang, Yide Zhang, Gengchen Mai, Lihong V. Wang, James Zou, Xiaoyu Wang, Ming-Hsuan Yang, Zhengzhong Tu}	NeurIPS 2025	Paper	Code
Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration _{Xin Lu, Xueyang Fu, Jie Xiao, Zihao Fan, Yurui Zhu, Zheng-Jun Zha}	arXiv	Paper	Code
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling _{Huaqiu Li, Yong Wang, Tongwen Huang, Hailang Huang, Haoqian Wang, Xiangxiang Chu}	arXiv	Paper	Code
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration _{Hao Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan}	ICCV 2025	Paper	Code
UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior _{I-Hsiang Chen, Wei-Ting Chen, Yu-Wei Liu, Yuan-Chun Chiang, Sy-Yen Kuo, Ming-Hsuan Yang}	CVPR 2025	Paper	Code
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration _{Haina Qin, Wenyang Luo, Zewen Chen, Yufan Liu, Bing Li, Weiming Hu, libin wang, DanDan Zheng, Yuming Li}	CVPR 2025	Paper	Code
UniRes: Universal Image Restoration for Complex Degradations	arXiv	Paper
Boosting All-in-One Image Restoration via Self-Improved Privilege Learning	arXiv	Paper	Code
Navigating Image Restoration with VAR's Distribution Alignment Prior _{Siyang Wang, Feng Zhao}	arXiv	Paper	Code
From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration _{Junyu Fan, Chuanlin Liao, Yi Lin}	arXiv	Paper
Manifold-aware Representation Learning for Degradation-agnostic Image Restoration _{Bin Ren, Yawei Li, Xu Zheng, Yuqian Fu, Danda Pani Paudel, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe}	arXiv	Paper	Code
Learning Dynamic Prompts for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	TIP 2025	Paper	Code
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery _{Hainuo Wang, Qiming Hu, Xiaojie Guo}	arXiv	Paper	Code
Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration _{Yuetong Liu, Yunqiu Xu, Yang Wei, Xiuli Bi, Bin Xiao}	arXiv	Paper	Code
RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration _{Sudarshan Rajagopalan, Kartik Narayan, Vishal M. Patel}	arXiv	Paper	Code
All-in-One Weather-Degraded Image Restoration Via Adaptive Degradation-Aware Self-Prompting Model _{Yuanbo Wen, Tao Gao, Ziqi Li, Jing Zhang, Kaihao Zhang, Ting Chen}	TMM 2025	Paper
AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning _{Sudarshan Rajagopalan, Vishal M. Patel}	AAAI 2025	Paper	Code
CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture _{Vladimir Frants, Sos Agaian, Karen Panetta, Peter Huang}	arXiv	Paper
DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model _{Zhanwen Liu, Sai Zhou, Yuchao Dai, Yang Wang, Yisheng An, Xiangmo Zhao}	arXiv	Paper
Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation _{Bin Ren, Eduard Zamfir, Zongwei Wu, Yawei Li, Yidi Li, Danda Pani Paudel, Radu Timofte, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe}	arXiv	Paper	Code
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie}	arXiv	Paper	Code
Beyond Degradation Conditions: All-in-One Image Restoration via HOG Transformers _{Jiawei Wu, Zhifei Yang, Zhe Wang, Zhi Jin}	arXiv	Paper	Code
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision _{Yuandong Pu, Le Zhuo, Kaiwen Zhu, Liangbin Xie, Wenlong Zhang, Xiangyu Chen, Peng Gao, Yu Qiao, Chao Dong, Yihao Liu}	arXiv	Paper	Code
Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration _{Yuanbo Wen, Tao Gao, Jing Zhang, Ziqi Li, Ting Chen}	AAAI 2025	Paper	Code
VL-UR: Vision-Language-guided Universal Restoration of Images Degraded by Adverse Weather Conditions _{Ziyan Liu, Yuxu Lu, Huashan Yu, Dong Yang}	arXiv	Paper
Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model _{Yingjie Zhou, Jiezhang Cao, Zicheng Zhang, Farong Wen, Yanwei Jiang, Jun Jia, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai}	arXiv	Paper
DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration _{Jiamei Xiong, Xuefeng Yan, Yongzhen Wang, Wei Zhao, Xiao-Ping Zhang, Mingqiang Wei}	arXiv	Paper
Content-Aware Transformer for All-in-one Image Restoration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu}	arXiv	Paper	Code
Cat-AIR: Content and Task-Aware All-in-One Image Restoration _{Jiachen Jiang, Tianyu Ding, Ke Zhang, Jinxin Zhou, Tianyi Chen, Ilya Zharkov, Zhihui Zhu, Luming Liang}	arXiv	Paper	Code
UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations _{Debabrata Mandal, Soumitri Chattopadhyay, Guansen Tong, Praneeth Chakravarthula}	arXiv	Paper	Code
Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal _{Rongxin Liao, Feng Li, Yanyan Wei, Zenglin Shi, Le Zhang, Huihui Bai, Meng Wang}	arXiv	Paper	Code
TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Models _{Wanglong Lu, Lingming Su, Jingjing Zheng, Vinícius Veloso de Melo, Farzaneh Shoeleh, John Hawkin, Terrence Tricco, Hanli Zhao, Xianta Jiang}	arXiv	Paper
Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks _{Haijin Zeng, Xiangming Wang, Yongyong Chen, Jingyong Su, Jie Liu}	CVPR2025	Paper	Code
Degradation-Aware Feature Perturbation for All-in-One Image Restoration _{Xiangpeng Tian, Xiangyu Liao, Xiao Liu, Meng Li, Chao Ren}	CVPR2025	Paper	Code
Multi-Agent Image Restoration _{Xu Jiang, Gehui Li, Bin Chen, Jian Zhang}	arXiv	Paper
MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration _{Zhehui Wu, Yong Chen, Naoto Yokoya, Wei He}	arXiv	Paper	Code
Dynamic Degradation Decomposition Network for All-in-One Image Restoration _{Huiqiang Wang, Mingchen Song, Guoqiang Zhong}	arXiv	Paper
USRNet: Unified Scene Recovery Network for Enhancing Traffic Imaging under Multiple Adverse Weather Conditions _{Yuxu Lu, Ai Chen, Dong Yang, Ryan Wen Liu}	arXiv	Paper	Code
Up-Restorer: When Unrolling Meets Prompts for Unified Image Restoration _{Minghao Liu, Wenhan Yang, Jinyi Luo, Jiaying Liu}	AAAI2025	Paper
Debiased All-in-one Image Restoration with Task Uncertainty Regularization _{Gang Wu, Junjun Jiang, Yijun Wang, Kui Jiang, Xianming Liu}	AAAI2025	Paper	Code
All-in-One Image Compression and Restoration _{Huimin Zeng, Jiacheng Li, Ziqiang Zheng, Zhiwei Xiong}	WACV2025	Paper	Code
RamIR: Reasoning and action prompting with Mamba for all-in-one image restoration _{Aiqiang Tang, Yan Wu, Yuwei Zhang}	Applied Intelligence	Paper
Universal Image Restoration Pre-training via Degradation Classification _{JiaKui Hu, Lujia Jin, Zhengjian Yao, Yanye Lu}	ICLR2025	Paper	Code
Complexity Experts are Task-Discriminative Learners for Any Image Restoration _{Eduard Zamfir, Zongwei Wu, Nancy Mehta, Yuedong Tan, Danda Pani Paudel, Yulun Zhang, Radu Timofte}	CVPR2025	Paper	Code
Adaptive Blind All-in-One Image Restoration _{David Serrano-Lozano, Luis Herranz, Shaolin Su, Javier Vazquez-Corral}	arXiv	Paper	Code
GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration _{Sudarshan Rajagopalan, Nithin Gopalakrishnan Nair, Jay N. Paranjape, Vishal M. Patel}	CVPR2025	Paper	Code
OmniRestore: Robust Universal Image Restoration from Combined and Unspecified Degradations _{Anjusree Karnavar, Yang Li, Jiajun Liu, Jun Zhou, Junhu Wang}	ICME 2025	Paper

2024

Paper	Avenue	Link	Code
Reference-Based Multi-Stage Progressive Restoration for Multi-Degraded Images _{Yi Zhang, Qixue Yang, Damon M. Chandler, Xuanqin Mou}	TIP 2024	Paper	Code
IPT-ILR: Image Pyramid Transformer Coupled With Information Loss Regularization for All-in-One Image Restoration _{Sai Yang, Bin Hu, Fan Liu, Xiaoxin Wu, Weiping Ding, Jun Zhou}	TCSVT 2024	Paper
Omni-Kernel Modulation for Universal Image Restoration _{Yuning Cui, Wenqi Ren, Alois Knoll}	TCSVT 2024	Paper
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity _{Jingbo Lin, Zhilu Zhang, Wenbo Li, Renjing Pei, Hang Xu, Hongzhi Zhang, Wangmeng Zuo}	arXiv	Paper	Code
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation _{Aiwen Jiang, Hourong Chen, Zhiwen Chen, Jihua Ye, Mingwen Wang}	arXiv	Paper	Code
MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers _{Ruoxi Zhu, Zhengzhong Tu, Jiaming Liu, Alan C. Bovik, Yibo Fan}	TIP2024	Paper	Code
Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding _{Yubin Gu, Yuan Meng, Xiaoshuai Sun, Jiayi Ji, Weijian Ruan, Rongrong Ji}	arXiv	Paper
AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations _{Jiawei Mao, Yu Yang, Xuesong Yin, Ling Shao, Hao Tang}	arXiv	Paper
All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Model _{Yuanbo Wen, Tao Gao, Ziqi Li, Jing Zhang, Kaihao Zhang, Ting Chen}	arXiv	Paper
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration _{Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun}	TPAMI2025	Paper	Code
Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers _{Jin Cao, Deyu Meng, Xiangyong Cao}	arXiv	Paper	Code
An Intelligent Agentic System for Complex Image Restoration Problems _{Kaiwen Zhu, Jinjin Gu, Zhiyuan You, Yu Qiao, Chao Dong}	ICLR2025	Paper	Code
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration _{Yuang Ai, Huaibo Huang, Ran He}	arXiv	Paper	Code
Adaptive Fuzzy Degradation Perception Based on CLIP Prior for All-in-One Image Restoration _{M. Shao, Y. Liu, Y. Cheng, Y. Wan, C. Wang}	IEEE Trans. Fuzzy Syst 2024	Paper
TANet: Triplet Attention Network for All-In-One Adverse Weather Image Restoration _{Hsing-Hua Wang, Fu-Jen Tsai, Yen-Yu Lin, Chia-Wen Lin}	ACCV2024	Paper	Code
Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration _{Chu-Jie Qin, Rui-Qi Wu, Zikun Liu, Xin Lin, Chun-Le Guo, Hyun Hee Park, Chongyi Li}	ECCV2024	Paper	Code
Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint _{Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, Lei Zhu}	ECCV2024	Paper	Code
Accurate Forgetting for All-in-One Image Restoration Model _{Xin Su, Zhuoran Zheng}	arXiv	Paper
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration _{Xu Zhang, Jiaqi Ma, Guoli Wang, Qian Zhang, Huan Zhang, Lefei Zhang}	TIP2025	Paper	Code
Learning A Low-Level Vision Generalist via Visual Task Prompt _{Xiangyu Chen, Yihao Liu, Yuandong Pu, Wenlong Zhang, Jiantao Zhou, Yu Qiao, Chao Dong}	ACMMM2024	Paper	Code
HAIR: Hypernetworks-based All-in-One Image Restoration _{Jin Cao, Yi Cao, Li Pang, Deyu Meng, Xiangyong Cao}	arXiv	Paper	Code
Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method _{Xin Su, Zhuoran Zheng, Chen Wu}	arXiv	Paper
UniProcessor: A Text-induced Unified Low-level Image Processor _{Huiyu Duan, Xiongkuo Min, Sijing Wu, Wei Shen, Guangtao Zhai}	ECCV2024	Paper	Code
Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration _{Xiaoyan Yu, Shen Zhou, Huafeng Li, Liehuang Zhu}	TCSVT 2024	Paper	Code
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models _{Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, Lei Zhu}	NIPS2024	Paper	Code
Training-Free Large Model Priors for Multiple-in-One Image Restoration _{Xuanhua He, Lang Li, Yingying Wang, Hui Zheng, Ke Cao, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, Man Zhou}	arXiv	Paper
Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration _{Yuhong Zhang, Hengsheng Zhang, Xinning Chai, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang}	arXiv	Paper	Code
Any Image Restoration with Efficient Automatic Degradation Adaptation _{Bin Ren, Eduard Zamfir, Yawei Li, Zongwei Wu, Danda Pani Paudel, Radu Timofte, Nicu Sebe, Luc Van Gool}	arXiv	Paper	Code
Restoring Images in Adverse Weather Conditions via Histogram Transformer _{Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, Xiaochun Cao}	ECCV 2024	Paper	Code
GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity _{Shuo Cao, Yihao Liu, Wenlong Zhang, Yu Qiao, Chao Dong}	ECCV2024	Paper
OneRestore: A Universal Restoration Framework for Composite Degradation _{Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He}	ECCV2024	Paper	Code
Learning Frequency-Aware Dynamic Transformers for All-In-One Image Restoration _{Zenglin Shi, Tong Su, Pei Liu, Yunpeng Wu, Le Zhang, Meng Wang}	arXiv	Paper
Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation _{Yuchuan Tian, Jianhong Han, Hanting Chen, Yuanyuan Xi, Guoyang Zhang, Jie Hu, Chao Xu, Yunhe Wang}	arXiv	Paper	Code
ConStyle v2: A Strong Prompter for All-in-One Image Restoration _{Dongqi Fan, Junhao Zhang, Liang Chang}	arXiv	Paper	Code
Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance _{Jiawei Mao, Juncheng Wu, Yuyin Zhou, Xuesong Yin, Yuanqi Chang}	arXiv	Paper	Code
All-In-One Medical Image Restoration via Task-Adaptive Routing _{Zhiwen Yang, Haowei Chen, Ziniu Qian, Yang Yi, Hui Zhang, Dan Zhao, Bingzheng Wei, Yan Xu}	MICCAI2024	Paper	Code
Efficient Degradation-aware Any Image Restoration _{Eduard Zamfir, Zongwei Wu, Nancy Mehta, Danda Pani Paudel, Yulun Zhang, Radu Timofte}	arXiv	Paper	Code
Harmony in Diversity: Improving All-in-One Image Restoration via Multi-Task Collaboration _{Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu}	ACMMM2024	Paper	Code
Referring Flexible Image Restoration _{Runwei Guan, Rongsheng Hu, Zhuhao Zhou, Tianlang Xue, Ka Lok Man, Jeremy Smith, Eng Gee Lim, Weiping Ding, Yutao Yue}	arXiv	Paper	Code
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models _{Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön}	CVPRW2024	Paper	Code
Joint Conditional Diffusion Model for Image Restoration with Mixed Degradations _{Yufeng Yue, Meng Yu, Luojie Yang, Yi Yang}	arXiv	Paper
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration _{Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang}	arXiv	Paper	Code
WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal _{Yulin Luo, Rui Zhao, Xiaobao Wei, Jinwei Chen, Yijie Lu, Shenghao Xie, Tianyu Wang, Ruiqin Xiong, Ming Lu, Shanghang Zhang}	arXiv	Paper
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation _{Yuning Cui, Syed Waqas Zamir, Salman Khan, Alois Knoll, Mubarak Shah, Fahad Shahbaz Khan}	ICLR2025	Paper	Code
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks _{Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin}	CVPR 2024	Paper	Code
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model _{Dian Zheng, Xiao-Ming Wu, Shuzhou Yang, Jian Zhang, Jian-Fang Hu, Wei-Shi Zheng}	CVPR2024	Paper	Code
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure _{De Cheng, Yanling Ji, Dong Gong, Yan Li, Nannan Wang, Junwei Han, Dingwen Zhang}	TMM 2024	Paper	Code
AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration _{Yuxu Lu, Dong Yang, Yuan Gao, Ryan Wen Liu, Jun Liu, Yu Guo}	arXiv	Paper	Code
InstructIR: High-Quality Image Restoration Following Human Instructions _{Marcos V. Conde, Gregor Geigle, Radu Timofte}	ECCV2024	Paper	Code
Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration _{Yimin Xu, Nanxi Gao, Zhongyun Shan, Fei Chao, Rongrong Ji}	arXiv	Paper	Code
Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy _{Xiangtao Kong, Chao Dong, Lei Zhang}	arXiv	Paper	Code
Improving Image Restoration through Removing Degradations in Textual Representations _{Jingbo Lin, Zhilu Zhang, Yuxiang Wei, Dongwei Ren, Dongsheng Jiang, Wangmeng Zuo}	CVPR2024	Paper	Code
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation _{Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang}	AAAI2024	Paper	Code

2023

Paper	Avenue	Link	Code
Textual Prompt Guided Image Restoration _{Qiuhai Yan, Aiwen Jiang, Kang Chen, Long Peng, Qiaosi Yi, Chunjie Zhang}	arXiv	Paper	Code
Decoupling Degradation and Content Processing for Adverse Weather Image Restoration _{Xi Wang, Xueyang Fu, Peng-Tao Jiang, Jie Huang, Mi Zhou, Bo Li, Zheng-Jun Zha}	arXiv	Paper
Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration _{Yuang Ai, Huaibo Huang, Xiaoqiang Zhou, Jiexiang Wang, Ran He}	CVPR2024	Paper
Language-driven All-in-one Adverse Weather Removal _{Hao Yang, Liyuan Pan, Yan Yang, Wei Liang}	CVPR2024	Paper
Test-Time Degradation Adaptation for Open-Set Image Restoration _{Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao, Xi Peng}	ICML2024	Paper	Code
Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement _{Yanyan Wei, Zhao Zhang, Jiahuan Ren, Xiaogang Xu, Richang Hong, Yi Yang, Shuicheng Yan, Meng Wang}	arXiv	Paper
Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal _{Yu-Wei Chen, Soo-Chang Pei}	IEEE Access2025	Paper	Code
Neural Degradation Representation Learning for All-In-One Image Restoration _{Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong}	TIP2024	Paper
AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion _{Yitong Jiang, Zhaoyang Zhang, Tianfan Xue, Jinwei Gu}	ECCV2024	Paper	Code
Unifying Image Processing as Visual Prompting Question Answering _{Yihao Liu, Xiangyu Chen, Xianzheng Ma, Xintao Wang, Jiantao Zhou, Yu Qiao, Chao Dong}	ICML2024	Paper
Controlling Vision-Language Models for Universal Image Restoration _{Ziwei Luo, Zheng Zhao, Thomas B. Schön}	ICLR2024	Paper	Code
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction _{Bingyu Xin, Meng Ye, Leon Axel, Dimitris N. Metaxas}	STACOM2023	Paper	Code
Prompt-based Ingredient-Oriented All-in-One Image Restoration _{Hu Gao, Depeng Dang}	TCSVT2024	Paper
All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation _{Cheng Zhang, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang}	ACMMM2023	Paper
Decomposition Ascribed Synergistic Learning for Unified Image Restoration _{Jinghao Zhang, Feng Zhao}	arXiv	Paper
RDM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration _{Yuanshuo Cheng, Mingwen Shao, Yecong Wan, Chao Wang}	Knowledge-Based Systems2024	Paper	Code
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration _{Jiaqi Ma, Tianheng Cheng, Guoli Wang, Qian Zhang, Xinggang Wang, Lefei Zhang}	arXiv	Paper
PromptIR: Prompting for All-in-One Blind Image Restoration _{Vaishnav Potlapalli, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan}	NeurIPS2023	Paper	Code
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions _{Tao Wang, Kaihao Zhang, Ziqian Shao, Wenhan Luo, Bjorn Stenger, Tong Lu, Tae-Kyun Kim, Wei Liu, Hongdong Li}	IJCV2024	Paper	Code
Multi-task Image Restoration Guided By Robust DINO Features _{Xin Lin, Jingtong Yue, Kelvin C.K. Chan, Lu Qi, Chao Ren, Jinshan Pan, Ming-Hsuan Yang}	arXiv	Paper
Generative Diffusion Prior for Unified Image Restoration and Enhancement _{Ben Fei, Zhaoyang Lyu, Liang Pan, Junzhe Zhang, Weidong Yang, Tianyue Luo, Bo Zhang, Bo Dai}	CVPR2023	Paper	Code
Context-aware Pretraining for Efficient Blind Image Decomposition _{Chao Wang, Zhedong Zheng, Ruijie Quan, Yifan Sun, Yi Yang}	CVPR2023	Paper
Ingredient-oriented Multi-Degradation Learning for Image Restoration _{Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao}	CVPR2023	Paper
Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions _{Yurui Zhu, Tianyu Wang, Xueyang Fu, Xuanyu Yang, Xin Guo, Jifeng Dai, Yu Qiao, Xiaowei Hu}	CVPR2023	Paper	Code
Adverse Weather Removal with Codebook Priors _{Tian Ye, Sixiang Chen, Jinbin Bai, Jun Shi, Chenghao Xue, Jingxia Jiang, Junjie Yin, Erkang Chen, Yun Liu}	ICCV2023	Paper
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models _{Ozan Özdenizci, Robert Legenstein}	TPAMI2023	Paper
Images Speak in Images: A Generalist Painter for In-Context Visual Learning _{Xinlong Wang, Wen Wang, Yue Cao, Chunhua Shen, Tiejun Huang}	CVPR2023	Paper	Code

2022

Paper	Avenue	Link	Code
All-In-One Image Restoration for Unknown Corruption _{Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng}	CVPR2022	Paper	Code
TAPE: Task-Agnostic Prior Embedding for Image Restoration _{Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian}	CVPR2022	Paper
Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model _{Wei-Ting Chen, Zhi-Kai Huang, Cheng-Che Tsai, Hao-Hsiang Yang, Jian-Jiun Ding, Sy-Yen Kuo}	CVPR2022	Paper	Code
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions _{Jeya Maria Jose Valanarasu, Rajeev Yasarla, Vishal M. Patel}	CVPR2022	Paper	Code
Blind Image Decomposition _{Junlin Han, Weihao Li, Pengfei Fang, Chunyi Sun, Jie Hong, Mohammad Ali Armin, Lars Petersson, Hongdong Li}	ECCV2022	Paper	Code

2021

Paper	Avenue	Link	Code
On Efficient Transformer-Based Image Pre-training for Low-Level Vision _{Wenbo Li, Xin Lu, Shengju Qian, Jiangbo Lu, Xiangyu Zhang, Jiaya Jia}	arXiv	Paper	Code
Pre-Trained Image Processing Transformer _{Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao}	CVPR2021	Paper	Code

2020

Paper	Avenue	Link	Code
All in One Bad Weather Removal Using Architectural Search _{Ruoteng Li, Robby T. Tan, Loong-Fah Cheong}	CVPR2020	Paper
A General Decoupled Learning Framework for Parameterized Image Operators _{Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen}	TPAMI2019	Paper

📊 All-in-one Image Restoration Performance Comparison

Performance Comparisons of AiOIR Models on Three Challenging Datasets

Category	Method	Venue & Year	Params	Dehazing SOTS	Deraining Rain100L	Denoising σ=15	Denoising σ=25	Denoising σ=50	Average	Approach
Single	LPN	CVPR'19	3M	20.84/0.828	24.88/0.784	26.47/0.778	24.77/0.748	21.26/0.552	23.64/0.738	Specific
	ADFNet	AAAI'23	8M	28.13/0.961	34.24/0.965	33.76/0.929	30.83/0.871	27.75/0.793	30.94/0.904	Specific
	DehazeFormer	TIP'23	25M	29.58/0.970	35.37/0.969	33.01/0.914	30.14/0.858	27.37/0.779	31.09/0.898	Specific
	DRSformer	CVPR'23	34M	29.02/0.968	35.89/0.970	33.28/0.921	30.55/0.862	27.58/0.786	31.26/0.902	Specific
Multiple	MPRNet	CVPR'21	16M	28.00/0.958	33.86/0.958	33.27/0.920	30.76/0.871	27.29/0.761	30.63/0.894	General
	Restormer	CVPR'22	26M	27.78/0.958	33.78/0.958	33.72/0.865	30.67/0.865	27.63/0.792	30.75/0.901	General
	NAFNet	ECCV'22	17M	24.11/0.960	33.64/0.956	33.18/0.918	30.47/0.865	27.12/0.754	29.67/0.844	General
	FSNet	TPAMI'23	13M	29.14/0.969	35.61/0.969	33.81/0.874	30.84/0.872	27.69/0.762	31.42/0.906	General
	MambaIR	ECCV'24	27M	29.57/0.970	35.42/0.969	33.88/0.931	30.95/0.874	27.74/0.793	31.51/0.907	General
All-in-One	DL	TPAMI'19	2M	26.92/0.931	32.62/0.931	33.05/0.914	30.41/0.861	26.90/0.740	29.98/0.875	parameterized image operator
	TKMANet	CVPR'22	29M	30.41/0.973	34.94/0.972	33.02/0.924	30.31/0.820	23.80/0.556	30.50/0.849	two-stage knowledge learning
	AirNet	CVPR'22	9M	27.94/0.962	34.90/0.967	33.92/0.933	31.26/0.888	28.00/0.797	31.20/0.910	contrastive-based & degradation-guided
	PIP_restormer	arXiv'23	27M	32.09/0.981	38.29/0.984	34.24/0.936	31.60/0.893	28.35/0.806	32.91/0.920	prompt-in-prompt learning
	IDR	CVPR'23	15M	29.87/0.970	36.03/0.971	33.89/0.931	31.32/0.884	28.04/0.798	31.83/0.911	ingredient-oriented learning
	PromptIR	NeurIPS'23	36M	30.58/0.974	36.37/0.972	33.98/0.933	31.31/0.888	28.06/0.799	32.06/0.913	prompt for AiOIR
	Gridformer	IJCV'23	34M	30.37/0.970	37.15/0.972	33.93/0.931	31.37/0.887	28.11/0.801	32.19/0.912	transformer with grid structure
	ProRes	arXiv'23	371M	28.38/0.938	33.68/0.954	32.10/0.907	30.18/0.863	27.58/0.779	30.38/0.888	degradation-aware visual prompt
	NDR	TIP'24	28M	28.64/0.962	35.42/0.969	34.01/0.932	31.36/0.887	28.10/0.798	31.51/0.910	neural degradation representation
	Art_PromptIR	ACM MM'24	36M	30.83/0.979	37.94/0.982	34.06/0.934	31.42/0.891	28.14/0.801	32.49/0.917	via multi-task collaboration
	AnyIR	arXiv'24	6M	31.38/0.979	37.90/0.981	33.95/0.933	31.29/0.889	28.03/0.797	32.51/0.916	local-global gated intertwining
	DaAIR	arXiv'24	6M	32.30/0.981	37.10/0.978	33.92/0.930	31.26/0.884	28.00/0.792	32.51/0.913	efficient degradation-aware
	MEASNet	arXiv'24	31M	31.61/0.981	39.00/0.985	34.12/0.935	31.46/0.892	28.19/0.803	32.85/0.919	multi-expert adaptive selection
	U-WADN	arXiv'24	6M	29.21/0.971	35.36/0.968	33.73/0.931	31.14/0.886	27.92/0.793	31.47/0.910	unified-width adaptive network
	Shi et al.	arXiv'24	-	29.20/0.972	37.50/0.980	34.59/0.941	31.83/0.900	28.46/0.814	32.32/0.921	frequency-aware transformers
	DyNet	arXiv'24	16M	31.98/0.981	38.71/0.983	34.11/0.936	31.44/0.892	28.18/0.803	32.88/0.920	dynamic pre-training
	Hair	arXiv'24	29M	30.98/0.979	38.59/0.983	34.16/0.935	31.51/0.892	28.24/0.803	32.70/0.919	hypernetworks-based
	LoRA-IR	arXiv'24	-	30.68/0.961	37.75/0.979	34.06/0.935	31.42/0.891	28.18/0.803	32.42/0.914	mixture of low-rank experts
	Up-Restorer	AAAI'25	28M	30.68/0.977	36.74/0.978	33.99/0.933	31.33/0.888	28.07/0.799	32.16/0.915	ADMM-solver-based design
	TUR_PromptIR	AAAI'25	36M	31.17/0.978	38.57/0.984	34.06/0.932	31.40/0.887	28.13/0.797	32.67/0.916	a novel loss function
	AdaIR	ICLR'25	29M	31.06/0.980	38.64/0.983	34.12/0.935	31.45/0.892	28.19/0.802	32.69/0.918	frequency mining and modulation
	DA-RCOT	TPAMI'25	50M	31.26/0.977	38.36/0.983	33.98/0.934	31.33/0.890	28.10/0.801	32.60/0.917	as an optimal transport problem
	ABAIR	arXiv'24	41M	33.53/0.984	38.69/0.982	34.18/0.935	31.38/0.890	28.25/0.804	33.21/0.919	a three-phase approach
	MoCE-IR	CVPR'25	25M	31.34/0.979	38.57/0.984	34.11/0.932	31.45/0.888	28.18/0.800	32.73/0.917	mixture-of-complexity-experts
	MTAIR	arXiv'24	-	31.34/0.983	39.15/0.984	34.14/0.936	31.50/0.893	28.24/0.805	32.87/0.920	Mamba-Transformer cross-dimensional
	DCPT_PromptIR	ICLR'25	35M	31.91/0.981	38.43/0.983	34.17/0.933	31.53/0.889	28.30/0.802	32.87/0.918	learn to classify degradation
	RamIR	APPL INTELL'25	22M	31.29/0.977	38.16/0.981	34.04/0.931	31.61/0.891	28.19/0.801	32.65/0.916	prompt-driven Mamba-based
	Cat-AIR	arXiv'25	-	31.49/0.980	38.43/0.983	34.11/0.935	31.44/0.892	28.14/0.803	32.72/0.919	content and task-aware framework
	DSwinIR	arXiv'25	24M	31.86/0.980	37.73/0.983	34.12/0.933	31.59/0.890	28.31/0.803	32.72/0.917	deformable sliding window transformer
	CPL_PromptIR	arXiv'25	36M	31.27/0.980	38.77/0.985	34.15/0.933	31.50/0.889	28.23/0.800	32.78/0.917	contrastive prompt regularization
	AnyIR	arXiv'25	6M	31.75/0.981	38.61/0.984	34.12/0.936	31.46/0.893	28.20/0.804	32.83/0.920	local-global gated mechanism
	MIRAGE	arXiv'25	10M	31.86/0.981	38.94/0.985	34.12/0.935	31.46/0.891	28.19/0.803	32.91/0.919	within the SPD manifold space
	BaryIR	arXiv'25	-	31.33/0.980	38.95/0.984	34.16/0.935	31.54/0.892	28.25/0.802	32.85/0.919	in continuous barycenter space
	SIPL_PromptIR	arXiv'25	39M	31.09/0.977	38.43/0.984	34.12/0.933	31.48/0.889	28.22/0.800	32.67/0.917	privilege learning
	TextPromptIR	arXiv'23	124M+110M	31.65/0.978	38.41/0.982	34.17/0.936	31.52/0.893	28.26/0.805	32.80/0.919	textual prompt for AiOIR
	InstructIR-3D	ECCV'24	16M+17M	30.22/0.959	37.98/0.978	34.15/0.933	31.52/0.890	28.30/0.804	32.43/0.913	natural language prompts
	DA-CLIP_IR-SDE	ICLR'24	49M+125M	26.83/0.962	35.85/0.972	31.43/0.889	25.05/0.605	18.33/0.308	27.50/0.747	degradation-aware vision-language model
	Perceive-IR	arXiv'24	42M+86M	30.87/0.975	38.29/0.980	34.13/0.934	31.42/0.888	28.09/0.797	32.56/0.915	prompt-based foundation model
	VLU-Net	CVPR'25	35M+88M	30.71/0.980	38.93/0.984	34.13/0.935	31.48/0.892	28.23/0.804	32.70/0.919	vision-language gradient descent-driven
	DFPIR	CVPR'25	31M+63M	31.87/0.980	38.65/0.982	34.14/0.935	31.47/0.893	28.25/0.806	32.88/0.919	degradation-aware feature perturbation

Performance Comparisons of AiOIR Models on Five Challenging Datasets

Type	Method	Venue & Year	Params	Dehazing (SOTS)	Deraining (Rain100L)	Denoising (BSD68)	Deblurring (Gopro)	Low-light (LOL)	Average	Approach
Single	ADFNet	AAAI'23	8M	24.18 / 0.928	32.97 / 0.943	31.15 / 0.882	25.79 / 0.781	21.15 / 0.823	27.05 / 0.871	Specific
	DehazeFormer	TIP'23	25M	25.31 / 0.937	33.68 / 0.954	30.89 / 0.880	25.93 / 0.785	21.31 / 0.819	27.42 / 0.875	Specific
	DRSformer	CVPR'23	34M	24.66 / 0.931	33.45 / 0.953	30.97 / 0.881	25.56 / 0.780	21.77 / 0.821	27.28 / 0.873	Specific
	HI-Diff	NeurIPS'23	24M	25.09 / 0.935	33.26 / 0.951	30.61 / 0.878	26.48 / 0.800	22.01 / 0.870	27.49 / 0.887	Specific
	Retinexformer	ICCV'23	2M	24.81 / 0.933	32.68 / 0.940	30.84 / 0.880	25.09 / 0.779	22.76 / 0.863	27.24 / 0.873	Specific
Multiple	SwinIR	ICCVW'21	1M	21.50 / 0.891	30.78 / 0.923	30.59 / 0.868	24.52 / 0.773	17.81 / 0.723	25.04 / 0.835	General
	MIRNet-v2	TPAMI'22	6M	24.03 / 0.927	33.89 / 0.954	30.97 / 0.881	26.30 / 0.799	21.52 / 0.815	27.34 / 0.875	General
	DGUNet	CVPR'22	17M	24.78 / 0.940	36.62 / 0.971	31.10 / 0.883	27.25 / 0.837	21.87 / 0.823	28.32 / 0.891	General
	Restormer	CVPR'22	26M	24.09 / 0.927	34.81 / 0.960	31.49 / 0.884	27.22 / 0.829	20.41 / 0.806	27.60 / 0.881	General
	NAFNet	ECCV'22	17M	25.23 / 0.939	35.56 / 0.967	31.02 / 0.883	26.53 / 0.808	20.49 / 0.809	27.76 / 0.881	General
	FSNet	TPAMI'23	13M	25.53 / 0.943	36.07 / 0.968	31.33 / 0.883	28.32 / 0.869	22.29 / 0.829	28.71 / 0.898	General
	MambaIR	ECCV'24	27M	25.81 / 0.944	36.55 / 0.971	31.41 / 0.884	28.61 / 0.875	22.49 / 0.832	28.97 / 0.901	General
All-in-One	DL	TPAMI'19	2M	20.54 / 0.826	21.96 / 0.762	23.09 / 0.745	19.86 / 0.672	19.83 / 0.712	21.05 / 0.743	parameterized image operator
	Transweather	CVPR'22	38M	21.32 / 0.885	29.43 / 0.905	29.00 / 0.841	25.12 / 0.757	21.21 / 0.792	25.22 / 0.836	weather type queries
	TAPE	ECCV'22	1M	22.16 / 0.861	29.67 / 0.904	30.18 / 0.855	24.47 / 0.763	18.97 / 0.621	25.09 / 0.801	task-agnostic prior
	AirNet	CVPR'22	9M	21.04 / 0.884	32.98 / 0.951	30.91 / 0.882	24.35 / 0.781	18.18 / 0.735	25.49 / 0.846	contrastive-based & degradation-guided
	IDR	CVPR'23	15M	25.24 / 0.943	35.63 / 0.965	31.60 / 0.887	27.87 / 0.846	21.34 / 0.826	28.34 / 0.893	ingredient-oriented learning
	PIP_Restormer	arXiv'23	27M	32.11 / 0.979	38.09 / 0.983	30.94 / 0.877	28.61 / 0.861	24.06 / 0.859	30.81 / 0.901	prompt-in-prompt learning
	PromptIR	NeurIPS'23	36M	26.54 / 0.949	36.37 / 0.970	31.47 / 0.886	28.71 / 0.881	22.68 / 0.832	29.15 / 0.904	prompt for AiOIR
	DASL_MPRNet	arXiv'23	15M	25.82 / 0.947	38.02 / 0.980	31.57 / 0.890	26.91 / 0.823	20.96 / 0.826	28.66 / 0.893	decomposition ascribed synergistic
	Gridformer	IJCV'23	34M	26.79 / 0.951	36.61 / 0.971	31.45 / 0.885	29.22 / 0.884	22.59 / 0.831	29.33 / 0.904	transformer with grid structure
	Art_PromptIR	ACM MM'24	36M	29.93 / 0.908	22.09 / 0.891	29.43 / 0.843	25.61 / 0.776	21.99 / 0.811	25.81 / 0.846	via multi-task collaboration
	DaAIR	arXiv'24	6M	31.97 / 0.980	36.28 / 0.975	31.07 / 0.878	29.51 / 0.890	22.38 / 0.825	30.24 / 0.910	efficient degradation-aware
	AnyIR	arXiv'24	6M	29.84 / 0.977	36.91 / 0.977	31.15 / 0.882	26.86 / 0.822	23.50 / 0.845	29.65 / 0.901	local-global gated intertwining
	MEASNet	arXiv'24	31M	31.05 / 0.980	38.32 / 0.982	31.40 / 0.888	29.41 / 0.890	23.00 / 0.845	30.64 / 0.917	multi-expert adaptive selection
	Hair	arXiv'24	29M	30.62 / 0.978	38.11 / 0.981	31.49 / 0.891	28.52 / 0.874	23.12 / 0.847	30.37 / 0.914	hypernetworks-based
	TUR_Transweather	AAAI'25	38M	29.68 / 0.966	33.09 / 0.952	30.40 / 0.869	26.63 / 0.815	23.02 / 0.838	28.56 / 0.888	a novel loss function
	AdaIR	ICLR'25	29M	30.53 / 0.978	38.02 / 0.981	31.35 / 0.889	28.12 / 0.858	23.00 / 0.845	30.20 / 0.910	frequency mining and modulation
	DA-RCOT	TPAMI'25	50M	30.96 / 0.975	37.87 / 0.980	31.23 / 0.888	28.68 / 0.872	23.25 / 0.836	30.40 / 0.911	as an optimal transport problem
	ABAIR	arXiv'24	41M	33.46 / 0.983	38.18 / 0.983	31.38 / 0.898	29.00 / 0.878	24.20 / 0.865	31.24 / 0.921	a three-phase approach
	MoCE-IR	CVPR'25	25M	30.48 / 0.974	38.04 / 0.982	31.34 / 0.887	30.05 / 0.899	23.00 / 0.852	30.58 / 0.919	mixture-of-complexity-experts framework
	DCPT_PromptIR	ICLR'25	35M	30.72 / 0.977	37.32 / 0.978	31.32 / 0.885	28.84 / 0.877	23.35 / 0.840	30.31 / 0.911	learn to classify degradation
	RamIR	APPL INTELL'25	22M	31.09 / 0.979	37.56 / 0.979	31.44 / 0.886	28.82 / 0.878	22.02 / 0.828	30.18 / 0.910	prompt-driven Mamba-based
	D3Net	arXiv'25	38M	32.57 / 0.965	38.35 / 0.973	31.73 / 0.860	32.70 / 0.851	26.49 / 0.857	32.36 / 0.901	cross-domain and dynamic decomposition
	Cat-AIR	arXiv'25	-	30.88 / 0.978	38.21 / 0.982	31.38 / 0.890	28.91 / 0.876	23.46 / 0.848	30.57 / 0.915	content and task-aware framework
	DSwinIR	arXiv'25	24M	30.09 / 0.975	37.77 / 0.982	31.34 / 0.885	29.17 / 0.879	22.64 / 0.843	30.19 / 0.913	deformable sliding window transformer
	CPL_PromptIR	arXiv'25	36M	30.82 / 0.978	38.20 / 0.983	31.41 / 0.887	28.72 / 0.874	23.65 / 0.855	30.55 / 0.915	contrastive prompt regularization
	AnyIR	arXiv'25	6M	31.41 / 0.980	38.51 / 0.983	31.37 / 0.891	28.85 / 0.883	23.11 / 0.856	30.65 / 0.919	local-global gated mechanism
	MIRAGE	arXiv'25	10M	31.45 / 0.980	38.92 / 0.985	31.41 / 0.892	28.10 / 0.858	23.59 / 0.858	30.68 / 0.914	within the SPD manifold space
	BaryIR	arXiv'25	-	31.12 / 0.976	38.05 / 0.981	31.43 / 0.891	29.30 / 0.888	23.38 / 0.852	30.66 / 0.918	in continuous barycenter space
	InstructIR-5D	ECCV'24	16M+17M	36.84 / 0.973	27.10 / 0.956	31.40 / 0.887	29.40 / 0.886	23.00 / 0.836	29.55 / 0.907	natural language prompts
	Perceive-IR	TIP'25	42M+86M	28.19 / 0.964	37.25 / 0.977	31.44 / 0.887	29.46 / 0.886	22.88 / 0.833	29.84 / 0.909	quality-aware degradation
	VLU-Net	CVPR'25	35M+88M	30.84 / 0.980	38.54 / 0.982	31.43 / 0.891	27.46 / 0.840	22.29 / 0.833	30.11 / 0.905	vision-language gradient descent-driven
	DFPIR	CVPR'25	31M+63M	31.64 / 0.979	37.62 / 0.978	31.29 / 0.889	28.82 / 0.873	23.62 / 0.852	30.60 / 0.914	degradation-aware feature perturbation
	CyclicPrompt	arXiv'25	30M+486M	33.02/0.983	37.03/0.989	31.33/0.941	29.42/0.925	21.79/0.837	30.52/0.935	cyclic prompt-driven universal framework

Performance Comparisons of AiOIR Models on All-Weather Datasets

Method	Snow	Rain+Fog	Raindrop	Average	Params
SwinIR	28.18/0.880	23.23/0.869	30.82/0.904	27.41/0.884	12M
MPRNet	28.66/0.869	30.25/0.914	30.99/0.916	29.30/0.900	16M
Restormer	29.37/0.881	29.22/0.907	31.21/0.919	29.93/0.902	26M
All-in-One	28.33/0.882	24.71/0.898	31.12/0.927	28.05/0.902	44M
Transweather	29.31/0.888	28.83/0.900	30.17/0.916	29.44/0.901	38M
AirNet	27.92/0.858	23.12/0.837	28.23/0.892	26.42/0.862	9M
WGWS-Net	28.91/0.856	29.28/0.922	32.01/0.925	30.07/0.901	6M
WeatherDiff	30.09/0.904	29.64/0.931	30.71/0.931	30.15/0.922	83M
TKMANet	30.24/0.902	29.92/0.917	30.99/0.927	30.38/0.915	29M
UtilityIR	29.47/0.879	31.16/0.927	32.01/0.925	30.88/0.910	26M
AWRCP	31.92/0.934	31.39/0.933	31.93/0.931	31.75/0.933	-
Histoformer	32.16/0.926	32.08/0.939	33.06/0.944	32.43/0.936	17M
LoRA-IR	32.28/0.930	32.62/0.945	33.39/0.949	32.76/0.941	-
T3-DiffWeather	32.37/0.936	31.99/0.937	32.66/0.941	32.34/0.938	69M+25M
MWFormer	30.92/0.908	30.27/0.912	31.91/0.927	31.03/0.916	170M
TUR_Transweather	30.62/0.909	29.75/0.907	31.61/0.933	30.66/0.916	38M
CyclicPrompt	32.16/0.927	32.81/0.937	32.57/0.945	32.51/0.936	30M+486M
DSwinIR	32.58/0.931	32.76/0.950	32.88/0.947	32.74/0.943	24M
DA2Diff	31.42/0.916	31.58/0.939	33.01/0.945	31.67/0.933	-
HOGformer	32.41/0.930	32.89/0.946	32.72/0.945	32.67/0.940	17M
CPL_PromptIR	32.27/0.928	32.16/0.942	32.73/0.943	32.39/0.938	36M
MODEM	32.52/0.929	33.10/0.941	33.01/0.943	32.87/0.938	20M

Method	Haze	Rain	Snow	Average	Params
the WeatherStream Dataset
NAFNet	22.20/0.803	23.01/0.803	22.11/0.826	22.44/0.811	17M
GRL	22.88/0.802	23.75/0.805	22.59/0.829	23.07/0.812	3M
Restormer	22.90/0.803	23.67/0.804	22.51/0.828	22.86/0.812	26M
MPRNet	21.73/0.763	21.50/0.791	20.74/0.801	21.32/0.785	16M
Transweather	22.55/0.774	22.21/0.772	21.79/0.792	22.18/0.779	38M
AirNet	21.56/0.770	22.52/0.797	21.44/0.812	21.84/0.793	9M
TKMANet	22.38/0.805	23.22/0.795	22.25/0.827	22.62/0.809	29M
WGWS-Net	22.78/0.800	23.80/0.807	22.72/0.831	23.10/0.813	6M
the Real-World Dataset
TKMANet	20.10/0.85	37.32/0.97	29.37/0.88	28.93/0.90	29M
TransWeather	17.33/0.82	33.64/0.93	26.92/0.86	26.71/0.86	38M
TUR_Transweather	20.38/0.88	39.78/0.98	29.72/0.91	29.96/0.92	38M
WGWS-Net	29.46/0.85	38.94/0.98	33.61/0.93	34.01/0.92	6M
DSwinIR	30.14/0.89	40.60/0.98	33.80/0.93	34.85/0.93	24M

Performance Comparisons of AiOIR Models on CDD-11 Datasets

Type	Method	Venue & Year	PSNR	SSIM	Params
One-to-One	MPRNet	CVPR'21	25.47	0.856	16M
One-to-One	MIRNetv2	TPAMI'22	25.37	0.854	6M
One-to-One	Restormer	CVPR'22	26.99	0.865	26M
One-to-One	DGUNet	CVPR'22	25.33	0.844	18M
One-to-One	NAFNet	ECCV'22	26.22	0.796	17M
One-to-One	SRUDC	ICCV'23	27.64	0.860	7M
One-to-One	Fourmer	ICML'23	23.44	0.789	6M
One-to-One	OKNet	AAAI'24	26.33	0.861	6M
One-to-Many	AirNet	CVPR'22	23.75	0.814	9M
One-to-Many	TransWeather	CVPR'22	23.13	0.804	38M
One-to-Many	WeatherDiff	TPAMI'23	24.09	0.799	83M
One-to-Many	PromptIR	NeurIPS'23	25.90	0.850	36M
One-to-Many	WGWS-Net	CVPR'23	26.96	0.861	6M
One-to-Many	HAIR	arXiv'24	27.85	0.866	29M
One-to-Composite	OneRestore	ECCV'24	28.47	0.878	6M
One-to-Composite	AllRestorer	arXiv'24	33.72	0.944	12M+88M
One-to-Composite	DA-CLIP_NAFNet	ICLR'24	26.56	0.860	86M+125M
One-to-Composite	MoCE-IR-S	CVPR'25	29.05	0.881	11M
One-to-Composite	DCPT_NAFNet	ICLR'25	30.66	0.891	68M
One-to-Composite	VL-UR	arXiv'25	28.76	0.879	-
One-to-Composite	MIRAGE	arXiv'25	29.33	0.887	10M
Step-by-Step	CoR_HAIR	arXiv'24	28.33	0.869	30M
Step-by-Step	CoR_OneRestore	arXiv'24	28.84	0.879	8M

Performance Comparisons of AiOIR Models on FoundIR's Real-World Datasets

Methods	Blur	Noise	JPEG	Haze	Rain	Raindrop	Lowlight	B+N	B+J	N+J	R+H	L+H	L+R	L+B	L+N	L+J	L+B+N	L+B+J	L+N+J	B+N+J	Average
Input	20.61/0.6544	37.30/0.9329	32.83/0.9530	13.47/0.6394	23.45/0.7791	20.76/0.6792	6.99/0.1802	22.85/0.7559	22.87/0.7450	38.45/0.9747	12.16/0.4774	9.94/0.3250	30.00/0.8935	10.55/0.4328	8.07/0.2535	8.50/0.3261	9.70/0.4079	9.01/0.4555	8.65/0.4984	22.44/0.7009	18.40/0.6033
DGUNet	21.86/0.7334	36.69/0.9494	29.80/0.8906	18.58/0.6762	25.47/0.8245	24.83/0.7924	16.16/0.6494	22.90/0.7633	22.86/0.7358	35.28/0.9564	18.79/0.4981	13.20/0.4182	30.66/0.9097	11.54/0.4922	12.56/0.5349	12.17/0.5433	10.60/0.4608	9.57/0.4897	9.64/0.5456	22.43/0.6945	20.27/0.6779
Restormer	21.81/0.7268	34.80/0.9311	29.08/0.8742	13.53/0.5316	24.70/0.7773	23.87/0.7395	8.64/0.3845	22.83/0.7474	22.76/0.7266	34.09/0.9412	12.88/0.4096	10.84/0.3110	29.72/0.8757	10.90/0.4487	8.40/0.3255	10.08/0.4492	9.74/0.4110	9.30/0.4647	10.30/0.5761	22.28/0.6836	18.52/0.6167
DiffIR	21.88/0.7346	37.69/0.9508	32.94/0.9313	19.06/0.7801	25.77/0.8249	25.34/0.8183	16.90/0.7311	22.90/0.7502	22.91/0.7373	38.97/0.9732	19.63/0.6275	18.78/0.7435	30.87/0.8971	22.10/0.7203	14.81/0.4651	25.66/0.8761	22.00/0.6862	21.68/0.7303	31.36/0.9613	22.48/0.6958	24.68/0.7817
IR-SDE	19.08/0.6395	23.67/0.8610	21.91/0.7738	13.67/0.5080	20.05/0.6541	20.61/0.6789	6.93/0.1578	19.77/0.6610	18.82/0.6118	22.35/0.8187	12.62/0.3905	9.64/0.2664	25.49/0.7651	10.21/0.3399	7.95/0.2049	8.44/0.2649	9.29/0.3274	8.63/0.3729	8.29/0.4027	18.64/0.5838	15.30/0.5141
RDDM	16.37/0.7183	14.94/0.8519	17.95/0.8419	11.12/0.6435	15.55/0.7118	15.47/0.6528	13.16/0.7027	15.82/0.7156	16.75/0.6822	18.23/0.9066	10.52/0.4568	13.87/0.3972	12.53/0.5537	17.26/0.6471	13.39/0.6025	14.09/0.5931	17.34/0.6457	15.98/0.6822	16.88/0.8222	17.76/0.6679	15.24/0.6747
X-Restormer	21.88/0.7325	35.86/0.9412	28.58/0.8646	16.47/0.6257	25.70/0.8076	26.11/0.8368	16.02/0.6404	22.90/0.7544	22.85/0.7321	33.83/0.9405	15.17/0.4354	14.75/0.4416	30.93/0.9026	19.38/0.6605	9.75/0.3866	18.66/0.7205	22.00/0.6841	13.63/0.5738	16.40/0.7810	22.41/0.6894	21.66/0.7075
All-in-One models
AirNet	18.07/0.5950	19.61/0.7588	19.42/0.5495	14.13/0.3792	17.61/0.4446	16.97/0.3233	6.60/0.1153	18.41/0.6054	19.22/0.6108	17.81/0.5239	13.53/0.2376	8.39/0.1452	22.41/0.6397	9.84/0.3293	7.75/0.2162	8.02/0.2210	8.76/0.2676	7.99/0.3122	7.83/0.3065	18.32/0.5282	14.03/0.4054
TransWeather	21.34/0.7103	30.12/0.8945	23.52/0.7296	17.72/0.5635	23.49/0.6886	22.94/0.6814	14.95/0.6295	22.19/0.7363	22.14/0.7105	25.59/0.8377	18.43/0.4245	15.99/0.4285	28.29/0.8663	21.35/0.6764	11.56/0.5181	19.16/0.6528	20.83/0.6607	19.64/0.6918	21.41/0.8068	21.64/0.6577	21.11/0.6782
IDR	17.75/0.6139	21.51/0.7896	17.96/0.5207	12.60/0.3581	16.37/0.4363	16.21/0.3422	6.96/0.1837	18.05/0.6243	18.21/0.6063	16.05/0.4826	11.40/0.2410	9.77/0.2377	23.42/0.7939	10.34/0.3976	7.92/0.2631	8.32/0.2696	9.51/0.3652	8.89/0.4170	8.34/0.3500	17.16/0.5209	13.83/0.4406
PromptIR	21.91/0.7339	36.57/0.9478	29.63/0.8842	15.36/0.4982	27.59/0.8411	25.83/0.8327	16.33/0.6353	22.93/0.7587	22.90/0.7360	35.08/0.9524	16.61/0.4985	15.36/0.4982	31.03/0.9039	20.29/0.6723	10.83/0.4499	21.52/0.7671	22.63/0.6924	12.40/0.5597	22.71/0.8616	22.47/0.6942	22.49/0.7209
DiffUIR	25.31/0.7979	34.48/0.9622	30.09/0.9390	19.97/0.8193	30.17/0.9350	26.98/0.8908	14.02/0.7101	24.44/0.8039	21.36/0.6915	31.96/0.9782	20.24/0.7268	19.31/0.7745	32.35/0.9255	18.97/0.6939	13.88/0.6262	19.98/0.8706	18.89/0.6705	18.64/0.6751	20.66/0.9338	23.72/0.7861	23.27/0.8105
DA-CLIP	20.92/0.6954	29.45/0.9027	25.77/0.7816	15.91/0.5399	23.04/0.6849	20.86/0.6490	17.34/0.7412	22.15/0.7293	21.36/0.6940	26.03/0.8602	13.97/0.3563	12.62/0.3220	21.58/0.7246	16.17/0.6241	15.70/0.6365	15.86/0.6048	15.30/0.6202	12.46/0.5774	15.34/0.7068	21.19/0.6589	19.15/0.6554
Real-ESRGAN	25.20/0.7868	34.46/0.9585	27.62/0.9108	22.07/0.8380	28.95/0.9226	28.94/0.9115	19.26/0.8709	23.48/0.7728	20.41/0.6562	29.71/0.9566	20.40/0.7153	21.79/0.8084	32.16/0.9116	21.95/0.7254	17.49/0.7358	22.89/0.8704	21.43/0.6612	19.49/0.6582	26.11/0.9496	21.40/0.7197	24.26/0.8173
SUPIR	20.92/0.6649	34.11/0.9035	24.52/0.7189	-	-	-	-	21.69/0.6828	21.34/0.6293	26.97/0.8003	-	-	-	-	-	-	-	-	-	20.18/0.5768	-
InstructIR	20.15/0.6801	38.58/0.9628	33.44/0.9378	16.85/0.7555	30.18/0.8997	21.05/0.6828	20.04/0.8542	21.70/0.7185	21.39/0.6814	39.90/0.9770	13.49/0.5535	13.52/0.4983	29.87/0.8866	17.43/0.6676	16.37/0.4625	18.06/0.7787	12.78/0.5392	17.39/0.7092	19.13/0.9105	22.42/0.6980	22.18/0.7426
AutoDIR	20.31/0.6946	36.84/0.9221	32.99/0.9280	15.23/0.6264	25.69/0.7711	20.82/0.6687	21.90/0.8288	21.90/0.7293	22.03/0.7088	37.55/0.9616	14.90/0.4213	14.50/0.4456	27.15/0.8576	19.14/0.6570	17.49/0.6900	16.14/0.6375	18.91/0.6499	16.91/0.6761	18.78/0.8122	22.37/0.6876	22.07/0.7187
FoundIR	25.93/0.7914	38.98/0.9647	34.03/0.9427	22.19/0.8492	34.29/0.9434	29.74/0.9160	18.98/0.8576	23.87/0.7737	29.58/0.8544	40.43/0.9795	21.80/0.7582	22.82/0.8048	33.96/0.9330	24.15/0.7808	18.95/0.7454	29.08/0.9098	23.56/0.7550	22.55/0.8181	33.46/0.9636	27.98/0.7452	27.81/0.8529

Star History

Citations

If our survey helps your research or work, please consider citing our paper. The following are BibTeX references:

@article{jiang2025survey,
  title={A survey on all-in-one image restoration: Taxonomy, evaluation and future trends},
  author={Jiang, Junjun and Zuo, Zengyuan and Wu, Gang and Jiang, Kui and Liu, Xianming},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={47},
  number={12},
  pages={11892--11911},
  year={2025}
}

Contributing

all-in-one-image-restoration

image-restoration

survey

Similar repos

ChaofWang/Awesome-Super-Resolution

Collect super-resolution related papers, data, repositories

3,099

ChunmingHe/awesome-diffusion-models-in-low-level-vision

A Repository for Diffusion-Model-related Papers in Low-level Vision

558

lixinustc/Awesome-diffusion-model-for-image-processing

one summary of diffusion-based image processing, including restoration, enhancement, coding,…

955

DarrenPan/Awesome-ICCV2023-Low-Level-Vision

A Collection of Papers and Codes in ICCV2023/2021 about low level vision

194

krantbrity/Single-Image-Reflection-Removal-Papers-and-Code-Collection

ChunmingHe/awesome-multimodal-large-language-models-in-low-level-vision

DarrenPan/Awesome-CVPR2024-Low-Level-Vision

A Collection of Papers and Codes in CVPR2023/2022 about low level vision

658

AlonzoLeeeooo/awesome-image-inpainting-studies

A collection of awesome image inpainting studies.

396

Significant stargazers

Ziyue Lin

3 followers · starred Aug 2025

Harbinzzy/All-in-One-Image-Restoration-Survey

README

A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

📚 Overview

🧭 Navigation

📢 News

📖 All-in-one Image Restoration Paper List

2026

2025

2024

2023

2022

2021

2020

📊 All-in-one Image Restoration Performance Comparison

Performance Comparisons of AiOIR Models on Three Challenging Datasets

Performance Comparisons of AiOIR Models on Five Challenging Datasets

Performance Comparisons of AiOIR Models on All-Weather Datasets

Performance Comparisons of AiOIR Models on Real-World Weather-Related Datasets

Performance Comparisons of AiOIR Models on CDD-11 Datasets

Performance Comparisons of AiOIR Models on FoundIR's Real-World Datasets

Star History

Citations

Contributing

Significant stargazers

Similar repos

Harbinzzy/All-in-One-Image-Restoration-Survey

README

A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

📚 Overview

🧭 Navigation

📢 News

📖 All-in-one Image Restoration Paper List

2026

2025

2024

2023

2022

2021

2020

📊 All-in-one Image Restoration Performance Comparison

Performance Comparisons of AiOIR Models on Three Challenging Datasets

Performance Comparisons of AiOIR Models on Five Challenging Datasets

Performance Comparisons of AiOIR Models on All-Weather Datasets

Performance Comparisons of AiOIR Models on Real-World Weather-Related Datasets

Performance Comparisons of AiOIR Models on CDD-11 Datasets

Performance Comparisons of AiOIR Models on FoundIR's Real-World Datasets

Star History

Citations

Contributing

Similar repos

Significant stargazers