reproducible-image-denoising-state-of-the-art

Collection of popular and reproducible single image denoising works. This collection is inspired by the summary by flyywh

Criteria: works must have codes available, and the reproducible results demonstrate state-of-the-art performances.

Check out the following collections of reproducible state-of-the-art algorithms:

• Video Denoising

• MultiSpectral / HyperSpepctral Denoising (to be ready)

• CS MRI (to be ready)

Denoising Algorithms (AWGN)

Filtering

• NLM [Web] [Code] [PDF]
  • A non-local algorithm for image denoising (CVPR 05), Buades et al.
  • Image denoising based on non-local means filter and its method noise thresholding (SIVP2013), B. Kumar
• BM3D [Web] [Code] [PDF]
  • Image restoration by sparse 3D transform-domain collaborative filtering (SPIE Electronic Imaging 2008), Dabov et al.
• PID [Web] [Code] [PDF]
  • Progressive Image Denoising (TIP 2014), C. Knaus et al.

Sparse Coding

• KSVD [Web] [Code] [PDF]
  • Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries (TIP 2006), Elad et al.
• LSSC [Web] [Code] [PDF]
  • Non-local Sparse Models for Image Restoration (ICCV 2009), Mairal et al.
• NCSR [Web] [Code] [PDF]
  • Nonlocally Centralized Sparse Representation for Image Restoration (TIP 2012), Dong et al.
• OCTOBOS [Web] [Code] [PDF]
  • Structured Overcomplete Sparsifying Transform Learning with Convergence Guarantees and Applications (IJCV 2015), Wen et al.
• GSR [Web] [Code] [PDF]
  • Group-based Sparse Representation for Image Restoration (TIP 2014), Zhang et al.
• TWSC [Web] [Code] [PDF]
  • A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising (ECCV 2018), Xu et al.

Classical External Priors

• EPLL [Web] [Code] [PDF]
  • From Learning Models of Natural Image Patches to Whole Image Restoration (ICCV2011), Zoran et al.
• GHP [[Web]][Code] [PDF]
  • Texture Enhanced Image Denoising via Gradient Histogram Preservation (CVPR2013), Zuo et al.
• PGPD [[Web]][Code] [PDF]
  • Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising (ICCV 2015), Xu et al.
• PCLR [[Web]][Code] [PDF]
  • External Patch Prior Guided Internal Clustering for Image Denoising (ICCV 2015), Chen et al.  

Low Rank

• SAIST [Web] [Code by request] [PDF]
  • Nonlocal image restoration with bilateral variance estimation: a low-rank approach (TIP2013), Dong et al.
• WNNM [Web] [Code] [PDF]
  • Weighted Nuclear Norm Minimization with Application to Image Denoising (CVPR2014), Gu et al.
• Multi-channel WNNM [Web] [Code] [PDF]
  • Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising (ICCV 2017), Xu et al.

Deep Denoising

• TNRD [Web] [Code] [PDF]
  • Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration (TPAMI 2016), Chen et al.
• RED [Web] [Code] [PDF]
  • Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (NIPS2016), Mao et al.
• DnCNN [Web] [Code] [PDF]
  • Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP2017), Zhang et al.
• MemNet [Web] [Code] [PDF]
  • MemNet: A Persistent Memory Network for Image Restoration (ICCV2017), Tai et al.
• NLCNN [Web] [Code] [PDF]
  • Non-Local Color Image Denoising with Convolutional Neural Networks (CVPR 2017), Lefkimmiatis.
• xUnit [Web] [Code] [PDF]
  • xUnit: Learning a Spatial Activation Function for Efficient Image Restoration (CVPR 2018), Kligvasser et al.
• UDNet [Web] [Code] [PDF]
  • Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018), Lefkimmiatis.
• Wavelet-CNN [Web] [Code] [PDF]
  • Multi-level Wavelet-CNN for Image Restoration (CVPR 2018), Liu et al.
• IRN [Web] [Code] [PDF]
  • Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks (ECCV 2018), Lefkimmiatis.
• FFDNet [Web] [Code] [PDF]
  • FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising (TIP 2018), Zhang et al.
• UDN [Web] [Code] [PDF]
  • Universal Denoising Networks- A Novel CNN Architecture for Image Denoising (CVPR 2018), Lefkimmiatis.
• N3 [Web] [Code] [PDF]
  • Neural Nearest Neighbors Networks (NIPS 2018), Plotz et al.
• NLRN [Web] [Code] [PDF]
  • Non-Local Recurrent Network for Image Restoration (NIPS 2018), Liu et al.
• RDN+ [Web] [Code] [PDF]
  • Residual Dense Network for Image Restoration (CVPR 2018), Zhang et al.
• FC-AIDE [Web] [Code] [PDF]
  • Fully Convolutional Pixel Adaptive Image Denoiser (ICCV 2019), Cha et al.
• FOCNet [Web] [Code] [PDF]
  • FOCNet: A Fractional Optimal Control Network for Image Denoising (CVPR 2019), Jia et al.

Unsupervised / Weakly-Supervised Deep Denoising

• Noise2Noise [Web] [TF Code] [Keras Unofficial Code] [PDF]
  • Noise2Noise: Learning Image Restoration without Clean Data (ICML 2018), Lehtinen et al.
• DIP [Web] [Code] [PDF]
  • Deep Image Prior (CVPR 2018), Ulyanov et al.
• Noise2Void [Web] [Code] [PDF]
  • Learning Denoising from Single Noisy Images (CVPR 2019), Krull et al.
• Noise2Self [Web] [Code] [PDF]
  • Noise2Self: Blind Denoising by Self-Supervision (ICML 2019), Batson and Royer
• Self-Supervised Denoising [Web] [Code] [PDF]
  • High-Quality Self-Supervised Deep Image Denoising (NIPS 2019), Laine et al.

Hybrid Model for Denoising

• STROLLR [PDF] [Code]
  • When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint for Image Restoration (ICASSP 2017), Wen et al.
• Meets High-level Tasks [PDF] [Code]
  • When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach (IJCAI 2018), Liu et al.
• USA [PDF] [Code]
  • Segmentation-aware Image Denoising Without Knowing True Segmentation (Arxiv), Wang et al.

Blind Denoising or Real Noise Removal

• RIDNet [Web] [Code] [PDF]
  • Real Image Denoising with Feature Attention (ICCV 2019), Anwar and Barnes.
• CBDNet [Web] [Code] [PDF]
  • Toward Convolutional Blind Denoising of Real Photographs (CVPR 2019), Guo et al.
• VDNNet [Web] [Code] [PDF]
  • Variational Denoising Network: Toward Blind Noise Modeling and Removal (NIPS 2019), Yue et al.

Image Noise Level Estimation

• SINLE [PDF] [Code] [Slides]
  • Single-image Noise Level Estimation for Blind Denoising (TIP 2014), Liu et al.

Novel Real Denoising Benchmark

• ReNOIR [Web] [Data] [PDF]
  • RENOIR - A Dataset for Real Low-Light Image Noise Reduction (Arxiv 2014), Anaya, Barbu.
• Darmstadt [Web] [Data] [PDF]
  • Benchmarking Denoising Algorithms with Real Photographs (CVPR 2017), Tobias Plotz, Stefan Roth.
• PolyU [Web] [Data] [PDF]
  • Real-world Noisy Image Denoising: A New Benchmark (Arxiv), Xu et al.
• SIDD [Web] [Data] [PDF]
  • A High-Quality Denoising Dataset for Smartphone Cameras (CV{R 2018), Abdelhamed et al.

Commonly Used Denoising Dataset

• Kodak [Web]
• USC SIPI-Misc [Web]
• BSD [Web]

Commonly Used Image Quality Metrics

• PSNR (Peak Signal-to-Noise Ratio) [Wiki] [Matlab Code] [Python Code]
• SSIM (Structural similarity) [Wiki] [Matlab Code] [Python Code]
• NIQE (Naturalness Image Quality Evaluator) [Web] [Matlab Code] [Python Code]