chang-xinhai/Awesome-Embodied-3DV

A curated map of 3D/4D perception, reconstruction, generation, simulation-ready assets, and world models for embodied AI.

Python

151 commits

updated Sep 23, 2026

See the code

README

Awesome-Embodied-3DV

A curated map of 3D/4D perception, reconstruction, generation, simulation-ready assets, and world models for embodied AI.

About

Awesome-Embodied-3DV is a curated list for the research space where 3D vision, 3D/4D reconstruction, 3D generation, simulation-ready assets, and embodied world models meet.

This repository focuses on:

Data Perception: depth, normals, active imaging, panoramic/fisheye, dense mapping, and 3D semantic understanding (detection, segmentation, grounding) that feed downstream systems
3D/4D Representation: 3DGS, 4DGS, NeRF/SDF, mesh, voxel, point, and hybrid structures
3D Reconstruction: offline, feed-forward, streaming, online, semantic, instance-level, and dynamic reconstruction
3D Generation: object-level, part-level, articulated, scene-level, editable, and simulation-ready asset generation
Embodiment & World Models: reconstruction-based world models, dynamic scene graphs, physical interaction & affordance, human-centric 3D, robotics integration, and agent-facing 3D grounding
Datasets, Benchmarks & Infrastructure: datasets, metrics, simulators, toolchains, and surveys for fast research orientation

This list is intentionally embodied-3DV-first. It includes 3D generation and 3DGS work only when it helps understand, build, evaluate, or deploy 3D assets and world models for embodied agents. It is not a generic catalog of all 3D generation, editing, rendering, compression, or graphics papers.

Daily candidate feed. The automatically updated arXiv Daily is a high-recall, topic-tagged candidate archive across the six areas above. It is deliberately broader than this curated README: papers are promoted here only after manual primary-source verification.

Must Read

Start here if you want the shortest path through the field.

Goal	Start with
Estimate temporally consistent video depth	Video Depth Anything, FlashDepth, ICDepth, ViGeo, DVD, RollingDepth
Deploy zero-shot monocular depth at the edge	ZipDepth, DepthART
Recover metric-scale geometry from RGB	MetricAnything, Metric DAv2, Depth Pro, UniDepthV2
Understand feed-forward 3D reconstruction	Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey, DUSt3R, MASt3R, VGGT
Track online / streaming 3D reconstruction	Dynamic 3D Gaussians, CUT3R, Spann3R, SLAM3R, StreamSplat, UniSim-SLAM
Study dynamic 4D feed-forward geometry	PAGE-4D, 4D-VGGT, DynamicVGGT
Learn representation foundations	3D Gaussian Splatting, NeRF, Instant-NGP, TensoRF
Generate object and simulation-ready assets	TRELLIS, Hunyuan3D 2.0, TripoSR, PartCrafter
Generate scenes and worlds	Infinigen, SceneDreamer, Text2Room, WonderWorld, EmbodiedGen V2
Build articulated objects	ArtGS, Articulate Anything, URDF-Anything, URDF-Anything+, PartNet-Mobility
Build an open-vocabulary 3D robot memory	CLIP-Fields, ConceptFusion, Open-Fusion, ConceptGraphs
Build persistent, action-conditioned 3D world models	Learning 3D Persistent Embodied World Models, GEN3C, NeoVerse, Genie 4D, BWM
Pick datasets and benchmarks	ScanNet, Tanks and Temples, DTU, Objaverse, GSO, HM3D, TransBiolab

News

[2026-08-04] Added a six-topic, automatically refreshed arXiv Daily candidate archive, with manual verification required before promotion to this curated list.
[2026-06-15] Added a dedicated 3D Editing taxonomy under 3D Generation, covering object-level, scene-level, and dynamic / 4D editing methods.
[2026-04-30] Initialized Awesome-Embodied-3DV with a six-part taxonomy for data perception, representations, reconstruction, generation, embodied world models, and infrastructure.

Awesome-Embodied-3DV

📡 1. Data Perception

Data perception covers the sensor-facing and semantic layers: extracting geometric priors (depth, normals), understanding 3D semantics (detection, segmentation, grounding), active-imaging signals, and dense maps from 2D images, video, or physical sensors.

1.1 Geometric Priors

1.1.1 Monocular High-Fidelity Depth

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-10	Metric Depth, 3DGS Relocalization, Sparse PnP Anchors, Temporal Memory	The Chinese University of Hong Kong, Shenzhen	RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting	arXiv	paper
2026-09-08	Diffusion Transformer, Single-Step Depth, Sharp Details, Dense Prediction	EPFL / HUAWEI Bayer Lab	Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation	SIGGRAPH Asia 2026	project / github
2026-09-08	Any Camera, Metric Point Cloud, Optional Intrinsics/Sparse Depth	Google DeepMind	OmniPoint: Universal Monocular Metric Pointcloud from Any Camera	ECCV 2026	project
2026-08-30	Transparent/Reflective Scenes, Bias-Aware Training, 30M Parameters	The University of Hong Kong	OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes	arXiv	project
2026-08-17	Pixel-Space Prediction, Fine Structures, Sharp Boundaries, Efficient Depth	The Chinese University of Hong Kong, Shenzhen	PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation	arXiv	project
2026-08-03	Geometry-Invariant Adaptation, Non-Lambertian Surfaces, Mirror/Glass Depth	Changchun Institute of Optics, Fine Mechanics and Physics, CAS	GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimation	arXiv	paper
2026-07-23	UAV Depth, Arbitrary Camera Pose, Metric Geometry	Aerospace Information Research Institute, CAS	DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV	arXiv	github
2026-07-20	Fine-Detail Geometry, Sparse Volumetric Refinement, Metric Scale	Tsinghua University	MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement	arXiv	project
2026-07-19	Lightweight Foundation Depth, Camera-Conditioned Metric Depth, Edge Deployment	University of Trento	DepthART: Scaling Foundation Monocular Depth to Tiny Models	ACM Multimedia 2026	project / github
2026-07-19	Metric Depth, Odometry Anchor, Recurrent SLAM	UC Berkeley	DROID-ANCHOR: Odometry-Anchored Recurrent Metric Depth Estimation	arXiv	paper
2026-07-17	Stereo Distillation, Epipolar Cues, Metric Depth	Michigan State University	Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth	arXiv	paper
2026-07-14	Auto-Regressive Depth, Coarse-to-Fine, Semantic Guidance	Sun Yat-sen University	ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning	arXiv	paper
2026-07-13	Metric Point Map, Pixel-Wise Calibration, Camera Diversity	The University of Hong Kong	FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry	ECCV 2026	project / github / model
2026-07-09	Lightweight Zero-Shot, 6.1M Parameters, On-Device Depth	University of Bologna	ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device	ECCV 2026	project / github
2026-05-27	Multi-Layer Depth, Transparent Surfaces, Point Process	Princeton University	SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping	CVPR 2026	github
2026-05-15	VLM, Dense Metric Depth, Spatial Reasoning	Zhejiang Univ	Unlocking Dense Metric Depth Estimation in VLMs	arXiv	project / github
2026-05-12	Sparse 3D Anchors, Relative-to-Metric, Graph Optimization	Tongji University	The Midas Touch for Metric Depth	CVPR 2026 Highlight	project
2026-03-28	Universal Camera, Metric Depth, Zero-Shot	Michigan State University	UniDAC: Universal Metric Depth Estimation for Any Camera	CVPR 2026	paper
2026-03-20	Transparent Objects, Generative Opacification, Monocular Depth, SeeClear-396k	University of California, Los Angeles	SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification	ECCV 2026	project / dataset
2026-03-17	Diffusion Prior, Real-World Data, Monocular Depth	Nanjing University of Science and Technology	Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation	CVPR 2026	paper
2026-03-04	Fine-Grained Geometry, Dual-Stream, Efficient	UMass Amherst	DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation	CVPR 2026	paper
2026-01-29	Sparse Metric Prompt, 20M Image-Depth Pairs, Metric Foundation Model	Li Auto Inc	MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources	ECCV 2026	project / github
2026-01-06	Arbitrary-Resolution, Neural Implicit, Fine Details	Zhejiang Univ	InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields	CVPR 2026	project / github
2025-12-13	Defocus Cue, Bokeh Stack, Metric Depth	Nanyang Tech Univ	Boosting Monocular Metric Depth Estimation via Bokeh Rendering	ICML 2026	project / github
2025-11-30	Deterministic Diffusion, Dense Geometry, Fine Details	HKUST(GZ)	Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model	arXiv	project / github
2025-11-13	Any-View Depth, Metric Geometry, Multi-View	ByteDance	Depth Anything 3: Recovering the Visual Space from Any Views	ICLR 2026	project / github
2025-10-27	Unified Generation+Depth, Diffusion Prior, Zero-Shot	HUST	More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models	NeurIPS 2025	github
2025-10-08	Pixel-Space Diffusion, Flying-Pixel-Free, Point Clouds	HUST	Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers	NeurIPS 2025	project / github
2025-09-29	VLM, Metric Depth, Sparse Supervision	Meta AI	DepthLM: Metric Depth From Vision Language Models	ICLR 2026 Oral	github
2025-07-03	Monocular Geometry, Metric Scale, Sharp Details	USTC / Microsoft	MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details	NeurIPS 2025	project / github
2025-04-16	Sliding Anchor, Unknown Intrinsics, Metric Scale	Shanghai Univ	Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image	arXiv	project / github
2025-02-27	Metric 3D Points, Self-Prompt Camera, Uncertainty	ETH Zurich	UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler	TPAMI 2026	github
2025-02-26	Cross-Context Distillation, Multi-Teacher, Fine-Detail Depth	Zhejiang Univ of Technology	Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator	arXiv	project / github
2024-11-27	Diffusion Distillation, Metric + Sharp, Boundary Detail	Qualcomm AI Research	SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation	CVPR 2025	project / github
2024-10-02	Metric Depth, Zero-Shot, Image Priors	Apple	Depth Pro: Sharp Monocular Metric Depth in Less Than a Second	ICLR 2025	github
2024-09-26	Diffusion, Single-Step, Dense Geometry	HKUST(GZ)	Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction	ICLR 2025	project / github
2024-06-13	Monocular Depth, Foundation Model, Metric DAv2	TikTok / HKU	Depth Anything V2	NeurIPS 2024	project / github / metric models
2024-03-27	Metric Depth, Universal, Zero-Shot	ETH Zurich	UniDepth: Universal Monocular Metric Depth Estimation	CVPR 2024	github
2024-01-19	Monocular Depth, Relative Depth, Foundation Model	TikTok / HKU	Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data	CVPR 2024	project
2023-12-04	Monocular Depth, Zero-Shot, Affine-Invariant	Intel Labs	Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation	CVPR 2024	project
2023-07-20	Metric 3D, Zero-Shot, Canonical Space	Alibaba	Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image	ICCV 2023	github
2021-03-24	ViT, Dense Prediction, Foundation, Depth	Intel Labs	DPT: Vision Transformers for Dense Prediction	ICCV 2021	github
2019-07-02	Robust Depth, Zero-Shot, Cross-Dataset, MiDaS	Intel Labs	MiDaS: Towards Robust Monocular Depth Estimation	TPAMI 2022	github

1.1.2 Temporally Consistent Video Depth

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-23	Unified Video Model, Depth+Normals, Temporal Consistency	Adobe Research	Unified Video Dense Prediction from Disjoint Data	arXiv	project
2026-07-02	Video Diffusion, In-Context Conditioning, Zero-Shot	HKUST	ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning	ECCV 2026	project
2026-05-28	Streaming Geometry, Dynamic Chunking, Depth+Normals	Zhejiang University	Towards Consistent Video Geometry Estimation	arXiv	project
2026-05-11	Camera Motion, 3D Consistency, Geometry Embedding	HUST	GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth	arXiv	github
2026-04-08	Post-Processing, Scalable, Single-Image Backbone	Seoul National University	VDPP: Video Depth Post-Processing for Speed and Scalability	CVPR 2026 ECV Workshop	paper
2026-04-02	Pose Refinement, Temporal Consistency, Monocular Video	Ajou University	PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency	CVPR 2026	paper
2026-03-12	Deterministic Diffusion, Generative Prior, Long Video	HKUST(GZ)	DVD: Deterministic Video Depth Estimation with Generative Priors	arXiv	project
2026-01-06	Temporal Stability, Monocular Video, Long Sequence	ETH Zurich	StableDPT: Temporal Stable Monocular Video Depth Estimation	arXiv	paper
2025-12-20	Endoscopic Geometry, Streaming Mamba, Metric Depth	Vanderbilt University	EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streams	arXiv	github / paper
2025-12-11	Sparse Keyframes, Propagation, Long-Video Consistency	ETH Zurich	Video Depth Propagation	3DV 2026	paper
2025-10-10	Online Inference, Low Memory, Temporal Consistency	Heidelberg University	Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption	arXiv	paper
2025-07-02	Diffusion Guidance, Scale Synchronization, Geometry Consistency	Tsinghua University	DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation	ICCV 2025	project
2025-04-09	2K Streaming, Mamba, 24 FPS	Netflix Eyeline Studios	FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution	ICCV 2025 Highlight	project / github
2025-01-21	Super-Long Video, Temporal Gradient, 30 FPS	ByteDance	Video Depth Anything: Consistent Depth Estimation for Super-Long Videos	CVPR 2025	project / github
2024-11-28	Long Video, Diffusion, Multi-Resolution Alignment	ETH Zurich	Video Depth without Video Models	CVPR 2025	project

1.1.3 Geometric Consistency Prior

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-06	Surface Normals, Transparent Objects, Rectified Flow, Edge Refinement	Zhejiang University	TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation	arXiv	project
2026-07-28	Stereo Depth, Walsh-Hadamard Mixing, Efficient Inference	Authors	WHTMix: Efficient Stereo Depth Estimation via Walsh-Hadamard Token Mixing	arXiv	paper
2026-07-22	Stereo Diffusion Transformer, Flow Matching, Progressive Refinement	Beihang University	STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching	arXiv	paper
2026-07-15	Vision Features, SE(3) Latent Geometry, Visual Navigation	Google DeepMind	SeeSE3: Emergence of 3D Space in Vision Features	arXiv	paper
2026-07-14	Heterogeneous Cameras, Metric Depth, Real-Time	D-Robotics	X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras	arXiv	project / github
2026-07-10	Video Generative Pretraining, Depth/Normals/Pose, Grounded 4D	Google DeepMind	Video Generation Models are General-Purpose Vision Learners	ECCV 2026	project
2026-07-06	Boundary-Centric Pretraining, Dense Spatial Perception	Robbyant	LingBot-Vision: Vision Pretraining for Dense Spatial Perception	arXiv	project / github
2026-03-02	Zero-Shot Stereo, Structure Prompt, Motion Prompt	HUST	PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts	CVPR 2026	paper
2025-12-11	Real-Time Stereo, Zero-Shot, Foundation Model	NVIDIA	Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching	CVPR 2026	paper
2025-07-22	Foundation Model, Depth/Normal/Pointmap, Multi-View	SJTU	Dens3R: A Foundation Model for 3D Geometry Prediction	ICLR 2026	paper
2025-04-15	Surface Normals, Foundation Model, Video, Temporal	Authors	NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors	ICCV 2025	project / paper
2025-03-21	Scalable Depth, Autoregressive, 2B Parameters	Baidu	DAR: Scalable Autoregressive Monocular Depth Estimation	CVPR 2025	project
2025-03-20	Universal Camera, Spherical 3D, Any Camera	ETH Zurich	UniK3D: Universal Camera Monocular 3D Estimation	CVPR 2025	github / paper
2025-03-11	LiDAR Surface Normal, Dataset, Point Cloud	TU Graz	LiSu: A Dataset and Method for LiDAR Surface Normal Estimation	CVPR 2025	github
2025-01-17	Stereo, Foundation Model, RAFT-Style, Zero-Shot	NVIDIA	FoundationStereo: Zero-Shot Stereo Matching	CVPR 2025 Oral / Best Paper Nomination	github
2025-01-17	Stereo, Robust, Zero-Shot, Non-Lambertian	Univ of Bologna	Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching	CVPR 2025	project
2024-12-11	Panoramic / Fisheye Depth, Zero-Shot Metric	Intel	Depth Any Camera: Zero-Shot Metric Depth from Any Camera	CVPR 2025	project
2024-10-24	Monocular Geometry, Pointmap, Affine-Invariant	USTC / Microsoft	MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images	CVPR 2025 Oral	github
2024-06-24	Normal Estimation, 3D Priors, Surface Geometry	Nvidia	StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal	SIGGRAPH Asia 2024	project
2024-03-27	Diffusion, Effective Conditioning, ViT Priors	IIT Delhi	ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth	CVPR 2024	github
2024-03-22	Metric 3D, Multi-Task, Geometry Foundation	Shanghai AI Lab	Metric3D v2: A Versatile Monocular Geometric Foundation Model	TPAMI 2025	project
2024-03-18	Geometry, Normals, Depth, Multi-Task	Apple	GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image	ECCV 2024	project
2024-03-01	Inductive Biases, Surface Normal, Oral	Imperial College London	DSINE: Rethinking Inductive Biases for Surface Normal Estimation	CVPR 2024 Oral	github
2023-12-04	High-Res, Patch-Wise, Model-Agnostic	KAUST	PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth	CVPR 2024	project
2023-09-25	Iterative Bins, Elastic, GRU, Classification-Regression	Beihang Univ	IEBins: Iterative Elastic Bins for Monocular Depth Estimation	NeurIPS 2023	github
2023-04-13	Internal Discretization, Continuous-Discrete, Depth	ETH Zurich	iDisc: Internal Discretization for Monocular Depth Estimation	CVPR 2023	github

1.2 3D Semantic Understanding

1.2.1 Open-Vocabulary 3D Segmentation & Grounding

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-08	Annotation-Free, Open-Vocabulary 3D, Language-Space Lifting	National Technical University of Athens	GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting	arXiv	paper
2026-07-21	Referring Segmentation, 3DGS, Generalized Grounding	Peking University	ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting	arXiv	project
2026-06-23	Open-Vocabulary BEV, 3DGS, Geometric Constraints	KAIST AI	Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints	ECCV 2026	paper
2026-06-04	Open-Vocabulary, Functionality Segmentation, Robotics	Authors	T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation	arXiv	paper
2026-05-07	Open-Vocabulary, Gaussian Feature Field, Codebook	TU Munich / Google	OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention	arXiv	paper
2025-11-20	Open-Vocabulary, SAM3, Promptable, DETR	Meta	SAM 3: Segment Anything with Concepts	ICLR 2026	github / paper
2025-04-03	Open-Vocabulary, Dual-Level Contrastive, Instance-Aware	BIGAI / Tsinghua	MPEC: Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding	CVPR 2025	project
2025-03-22	Training-Free, MLLM Caption, Voxel Grouping	NVIDIA Research Taiwan	OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding	CVPR 2026	project
2025-03-19	SAM-2, 3D Tracking, Dynamic Programming	VinAI	Any3DIS: Open-Vocabulary 3D Instance Segmentation with SAM-2	CVPR 2025	paper
2025-03-13	Open-Vocabulary, LLM Canonical, Part Segmentation	Shandong Univ / Tencent	CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation via LLM-Guided Canonical Spatial Modeling	CVPR 2026 Oral	github
2025-03-12	Functional 3D, CoT, VLM, Training-Free, Highlight	Authors	Fun3DU: Functional 3D Scene Understanding via Chain-of-Thought	CVPR 2025 Highlight	paper
2025-01-02	Panoptic, Open-Vocabulary, 3D Gaussian Splatting	NUS	PanoGS: Gaussian-based Panoptic Open-Vocabulary 3D Scene Understanding	CVPR 2025	project
2024-12-13	Open-Vocabulary 3D, Structured Super-Gaussians, Segmentation	Google	SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians	3DV 2026	paper
2024-12-12	Open-Vocabulary, Foundation Dataset, Mask-Text Pairs	NVIDIA	Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation	CVPR 2025	github
2024-07-02	Open-Vocabulary, Mask-Snap-Lookup, Indoor/Outdoor	HKUST	OpenIns3D: Open-Vocabulary 3D Segmentation with Mask-Snap-Lookup	ECCV 2024	github
2024-04-01	Region-Level, Point-Language Contrastive, Multi-VLM	HKU	RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding	CVPR 2024	project / github
2024-03-19	Open-Vocabulary, MLLM, Point-Entity-Text, nuScenes	MPI	OV3D: Open-Vocabulary 3D Understanding with Multi-Modal Alignment	CVPR 2024	paper
2024-03-19	2D-Guided, 3D Proposals, SAM, Instance	VinAI / IBM	Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D-Guided Mask Generation	CVPR 2024	github
2024-03-15	Training-Free, View-Consensus, Instance	PKU	MaskClustering: View-Consensus for 3D Instance Segmentation	CVPR 2024	paper
2024-03-11	Zero-Shot, Superpoint, SAM, Scene Graph	PKU	SAI3D: Zero-Shot 3D Instance Segmentation by Scene-Aware Incremental Merging	CVPR 2024	github
2024-01-31	Segment Anything, 3D Gaussians, Interactive	Zhejiang University	SAGD: Boundary-Enhanced Segment Anything in 3D Gaussians	arXiv	github
2024-01-04	2D+3D Unified, Single Model, Highlight	Authors	ODIN: A Single Model for 2D and 3D Segmentation	CVPR 2024 Highlight	github
2023-12-26	Open-Vocabulary 3DGS, Segmentation, Language	ETH Zurich	LangSplat: 3D Language Gaussian Splatting	CVPR 2024 Highlight	project / github
2023-11-17	Unified, Semantic+Instance+Panoptic, Single Transformer	Samsung	OneFormer3D: One Transformer for Unified 3D Segmentation	CVPR 2024	github
2023-06-23	Open-Vocabulary 3D Instance, Mask Proposals, CLIP	ETH Zurich	OpenMask3D: Open-Vocabulary 3D Instance Segmentation	NeurIPS 2023	project
2023-06-06	Segment Anything 3D, Point Cloud, Interactive	VAST AI	SAM3D: Segment Anything in 3D Scenes	CVPR 2024	github
2023-03-16	Open-Vocabulary, 3D Scene, Language Field	UC Berkeley	LERF: Language Embedded Radiance Fields	ICCV 2023	project / github
2022-11-28	Open-Vocabulary 3D, Point Cloud, Segmentation	ETH Zurich	OpenScene: 3D Scene Understanding with Open Vocabularies	CVPR 2023	project / github

1.2.2 3D Instance & Panoptic Segmentation

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-06-08	Feed-Forward, Open-Vocabulary, Panoptic	Authors	EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation	ICML 2026	github
2025-07	Feed-Forward, Panoramic, DUSt3R-Based	Authors	PanSt3R: Single-Feed 3D Geometry and Panoptic Segmentation	ICCV 2025	paper
2025-05-14	MoE, Multi-Dataset, PTv3, CLIP Alignment	UVA	Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation	ICLR 2026	project
2025-03-01	Bayesian 3DGS, Training-Free, EIG	Sony	B3-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG	CVPR 2026	project
2025-01-14	End-to-End, 2D-to-3D Lifting, 3DGS	CUHK	Unified-Lift: Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting	CVPR 2025	github
2025-01-10	Unsupervised Panoptic, Scene-Centric	TU Darmstadt	CUPS: Scene-Centric Unsupervised Panoptic Segmentation	CVPR 2025 Highlight	github
2025-01-06	Zero-Shot Instance, SAM Prompts in 3D	CUHK-SZ / MSRA	SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation	3DV 2025	github
2024-07-03	3D Panoptic, LiDAR, Multi-Scene	Tsinghua	UniSeg3D: Unified 3D Panoptic Segmentation	CVPR 2023	github
2024-03-25	Unsupervised 3D Instance, Indoor	Authors	UnScene3D: Unsupervised 3D Instance Segmentation	CVPR 2024	paper
2024-03-24	Unified 6 Tasks, Single Transformer	HUST	UniSeg3D: Unified 3D Segmentation with Transformer	NeurIPS 2024	paper
2023-12-15	Point Cloud, Foundation Model, 3D Understanding	Shanghai AI Lab	Point Transformer V3: Simpler, Faster, Stronger	CVPR 2024	github
2022-10-06	3D Instance Segmentation, Transformer, Point Cloud	ETH Zurich	Mask3D: Mask Transformer for 3D Semantic Instance Segmentation	ICRA 2023	github

1.2.3 3D Visual Grounding & Spatial Reasoning

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-23	3D-Aware VLM, Implicit+Explicit Geometry, RGB Video	Nanyang Technological University	3D-Aware VLMs with Implicit and Explicit Geometries	ECCV 2026	github
2026-07-14	3D Language Fields, Ambiguity Awareness, Object Retrieval	Authors	SaaF: Scene-Specific Ambiguity-Aware 3D Language Fields towards Interactive Real-World Object Retrieval	arXiv	paper
2026-06-23	Agentic, Cognitive Map, Zero-Shot 3D	Sichuan University	Agentic Collaborative Cognition for Zero-Shot 3D Understanding	ECCV 2026	project
2026-06-22	Map-Grounded, MV3D-VQA, Dense Reward	KAIST	Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views	ECCV 2026	paper
2026-06-17	Panoramic Reprojection, 3D VLM, Spatial Reasoning	Technical University of Munich	OneCanvas: 3D Scene Understanding via Panoramic Reprojection	arXiv	project
2026-06-04	Part-Aware 3D-MLLM, Scene Understanding, Grounding	Xiamen University	PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding	arXiv	project
2025-10-19	Grounded CoT, 3D Reasoning, SceneCOT-185K Dataset	BIGAI / PKU / Tsinghua	SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes	ICLR 2026	paper
2025-07	Scene Graph, LLM, Relation Encoding	AIRI	3DGraphLLM: 3D Scene Graph Learning with LLMs	ICCV 2025	paper
2025-03-19	Gesture+Language, Embodied Reference, +30%	Authors	Ges3ViG: 3D Embodied Reference Understanding with Pointing Gestures	CVPR 2025	paper
2025-03-19	Geometry VLM, Unified 3D Recon + Spatial Reasoning	Shanghai AI Lab / UCLA / SJTU	G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning	CVPR 2026	github
2025-03-12	Dense Grounding, 6.2M Pairs, Hallucination Benchmark	UMich	3D-GRAND: A Million-Scale Dataset for 3D Grounding	CVPR 2025	project
2025-03-11	3D-Informed, Spatial Reasoning, Highlight	JHU	SpatialLLM: Spatial Reasoning with 3D-Informed LLMs	CVPR 2025 Highlight	paper
2025-03-10	LLM Attention, Scene Magnifier, Cross-Room	SCUT	LSceneLLM: LLM-Attention Adaptive 3D Scene Understanding	CVPR 2025	paper
2025-01-12	LVLM-Guided, Hierarchical Feature, 3DGS	Fudan / NTU	ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding	CVPR 2025	project
2025-01-04	Generalist 3D LMM, Omni Superpoint Transformer	Adelaide / Microsoft	3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer	CVPR 2025	github
2024-07-18	Object Identifiers, 3D VL, Unified Tasks	ZJU	Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers	NeurIPS 2024	github
2024-07-15	Million-Scale 3D VL, Multi-Level Contrastive	BIGAI	SceneVerse: Scaling 3D Vision-Language Learning for Grounding	ECCV 2024	project
2024-06-06	Zero-Shot 3D Grounding, 2D VLM Transfer	NUS	SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding	CVPR 2025	project
2024-04-03	Open-Vocabulary 3D Scene Graph, Open Relations	Bosch	Open3DSG: Open-Vocabulary 3D Scene Graph Generation	CVPR 2024	paper
2024-03-08	Interactive 3D, Language Assistant, Point Cloud	CUHK	LL3DA: Visual Interactive Instruction Tuning for 3D Language Assistant	CVPR 2024	github
2024-03	CLIP Cross-Modal, Contrastive, Scene Graph	Authors	CCL-3DSGG: CLIP-Driven Contrastive Learning for 3D Scene Graph Generation	CVPR 2024	paper
2023-11-21	Generalist Embodied 3D Agent, VLA, ICML	BIGAI	LEO: An Embodied Generalist Agent in 3D World	ICML 2024	project
2023-08-08	3D Visual Grounding, Referring Expression, Point Cloud	Peking University	3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment	ICCV 2023	github
2023-07-24	3D VQA, 3D Captioning, Scene Understanding	Shanghai AI Lab	3D-LLM: Injecting the 3D World into Large Language Models	NeurIPS 2023	project / github
2023-03	3D Language Pre-training, Captioning, QA	Authors	3D-VLP: 3D Vision-Language Pre-training with Contextual Scene	CVPR 2023	paper

1.3 Active Imaging & Sensors

1.3.1 Structured Light & Active Stereo

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-29	iToF, Sensor-Intrinsic Uncertainty, Heteroscedastic Restoration	Tsinghua University	Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration	arXiv	paper
2026-07-27	Neural Structured Light, Metric Depth, Online SLAM	Peking University	NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction	ACM MM 2026	paper
2026-07-20	Projector-Camera, Feed-Forward 3DGS, Active Illumination	Ningbo University	FF-ProCams: Feed-Forward Gaussian Splatting for Projector-Camera System	arXiv	github
2026-06	Active Stereo, 2DGS Supervision, RealSense Dataset	Hangzhou Dianzi University	GS-ASM: 2DGS-Supervised Active Stereo Matching	CVPR 2026	paper
2026-05-07	Adaptive 4D Illumination, Shape+Reflectance, Differentiable Capture	Zhejiang University	Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectance	CVPR 2026	paper
2026-03	Multi-Projector Structured Light, One-Shot Scan, Neural SDF	Kyushu University	Multi-view Stereo with Multiple Projectors for Oneshot Entire Shape Scan based on Neural SDF and DSSS Demultiplexing	WACV 2026	paper
2026-02-05	Latent Diffusion, Fringe Projection, Reflective Objects	Yonsei University	LD-SLRO: Latent Diffusion Structured Light for 3-D Reconstruction of Highly Reflective Objects	arXiv	paper
2025-12-16	Single-Shot, Neural Feature Decoding, Robust Correspondence	Peking University	Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding	SIGGRAPH Asia 2025	project
2025-12	Event Camera, HDR Measurement, Confidence Stereo	USTC	Event-based HDR Structured Light	NeurIPS 2025	github
2025-03-08	Active Stereo, Phase Speckle, Cross-Scene Generalization	Southwest Jiaotong University	RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization	arXiv	paper
2025-02	Unsupervised Structured Light, Neural SDF, Shadow-Aware	Kyushu University	Neural SDF for Shadow-Aware Unsupervised Structured Light	WACV 2025	paper
2025-01-13	Matching-Free, Volume Rendering, Monocular Structured Light	USTC	Matching-Free Depth Recovery from Structured Light	arXiv	paper
2024-10-20	Neural SDF, One-Shot Scan, Low-Light/Underwater	Kyushu University	ActiveNeuS: Neural Signed Distance Fields for Active Stereo	3DV 2024	paper
2024-06-06	Virtual Pattern Projection, Depth Fusion, In-the-Wild Stereo	University of Bologna	Active Stereo in the Wild through Virtual Pattern Projection	arXiv	github
2024-06	Neural Inverse, Dense Depth, 3-4 Patterns	University of Toronto	TurboSL: Dense, Accurate and Fast 3D by Neural Inverse Structured Light	CVPR 2024	project
2023-06-17	Structured Light, Phase Unwrapping, Learning	Nanjing University	Deep Learning-Based Structured Light 3D Imaging: A Survey	arXiv	survey
2018-11-27	Event Camera, Active Stereo, Depth	Tsinghua University	Event-Based Structured Light for Depth Reconstruction	IJCAS 2024	paper

1.3.2 Panoramic & Fisheye Perception

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-06-16	Wide-FOV, Egocentric, 4D Hand-Object	Rice University	EgoInfinity: A Web-Scale 4D Hand-Object Interaction Data Engine for Any-View Robot Retargeting and Video-to-Action Robot Learning	arXiv	project / dataset
2026-03-19	Panoramic Depth, VGGT, Geometry Consistency	Singapore University of Technology and Design	VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation	CVPR 2026	paper
2026-03-18	Panoramic Reconstruction, Permutation-Equivariant, 360°	Cornell	PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery	CVPR 2026	paper
2026-01-25	RGB-D, Depth Completion, Reflective/Transparent	Robbyant	LingBot-Depth: Masked Depth Modeling for Spatial Perception	arXiv	github / paper
2025-12-18	Panoramic Foundation Model, Multi-Camera, Metric Depth	Insta360 Research	Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation	CVPR 2026	paper
2025-01	Fisheye, Real-Time, Cassini, Multi-View	Sun Yat-Sen Univ	OmniStereo: Real-time Omnidirectional Depth with Multiview Fisheye Cameras	CVPR 2025	github
2024-06-19	Panoramic Depth, Semi-Supervised, Mobius	HKUST(GZ)	PanDA: Panoramic Depth Anything with Mobius Spatial Augmentation	CVPR 2025	project
2024-03-25	360 Depth, Bi-Projection, ERP+ICOSAP	HKUST(GZ)	Elite360D: Efficient 360 Depth Estimation via Bi-Projection Fusion	CVPR 2024	github
2021-09-06	360 Depth, Indoor, Panoramic Images	CERTH	Pano3D: A Holistic Benchmark and a Solid Baseline for 360 Depth Estimation	CVPRW 2021	project / github

1.3.3 Event-Based & Time-of-Flight Imaging

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-26	Active Event Stereo, High-Speed Depth, 150 FPS	Authors	Towards Ultrafast Depth Sensing Via Active Event-based Stereo Vision	TPAMI 2026	paper
2026-07-17	Event Camera, Feed-Forward 3D, Temporal Aggregation	Zhejiang University	Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation	arXiv	paper
2026-06	RGB+ToF Histogram, High-Resolution Metric Depth, Lightweight	Tongji University	LiteSense: Lifting Lightweight ToF with RGB for High-Resolution Metric Depth Estimation	CVPR 2026 Highlight	paper
2026-06	Sparse dToF, Zero-Shot Completion, Sensor Generalization	KAIST	Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors	CVPR 2026	paper
2026-06	Image-Event Fusion, Monocular Depth, Linear Complexity	Peking University	AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimation	CVPR 2026	paper
2026-06	Event-Image Depth, Hypothesis Volume, Iterative Refinement	Southeast University	Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation	CVPR 2026	paper
2026-04-16	Event-Frame Stereo, Cross-Modal Prompting, High Dynamic Range	Southeast University	Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo	CVPR 2026	paper
2026-04-02	Event Stereo, Data Factory, Cross-Modal Distillation	University of Bologna	EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors	CVPR 2026	project
2026-02-03	Event Camera, Neural SDF, Single-Camera Mesh	Saarland University	EventNeuS: 3D Mesh Reconstruction from a Single Event Camera	3DV 2026	project / github / dataset
2025-12-20	Event Camera, Structured Light, Real-Time RGB-D	Polytechnique Montreal	E-RGB-D: Real-Time Event-Based Perception with Structured Light	arXiv	github
2025-09-18	Event Camera, Depth Estimation, Any-to-Any	Shanghai AI Lab	Depth AnyEvent: Event Camera Based Monocular Depth Estimation via Dense Correspondence Distillation	arXiv	paper
2025-09-08	Event Camera, Multispectral, Structured Light	ETH Zurich	Event Spectroscopy: Event-based Multispectral and Depth Sensing using Structured Light	arXiv	paper
2025-05-28	Burst-Encodable ToF, Long-Range Depth, Hardware-Aware Coding	Nanjing University	Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing	NeurIPS 2025	github
2025-05	Event, Distillation, Confidence-Guided, Pseudo-Labels	NUS	Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Depth	NeurIPS 2025	paper
2025-04-23	ToF, Sparse Depth, 3DGS, SLAM	Authors	ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth	ICCV 2025	paper / paper
2025-04-22	Event Camera, Ray Density, 3D Conv, Spotlight	TU Berlin	DERD-Net: Learning Depth from Event-based Ray Densities	NeurIPS 2025 Spotlight	github
2025-03-03	dToF, Video Depth Completion, Frequency Selective	Authors	SVDC: Consistent Direct Time-of-Flight Video Depth Completion	CVPR 2025	paper / paper
2024-10-10	Event Camera, Pose-Free, Gaussian Splatting, Highlight	Zhejiang Univ	IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera	CVPR 2025 Highlight	github

1.3.4 Radar & RF Imaging

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-10	mmWave Radar, Complex-Valued Point Splatting, Material Model, Novel Views	Cornell Tech	3D Point Splatting for mmWave Radar Novel View Synthesis	arXiv	paper
2026-09-09	mmWave Radar, Metric Depth, Smoke/Fog/Darkness, 95K Frames	Rice University	GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradation	MobiCom 2026	project+data

1.4 Dense Mapping Systems

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-09	RGB-D 3DGS, Online Reconstruction, Reactive Control	Mitsubishi Electric Research Laboratories	SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control	ICRA 2026	paper
2026-07-08	Geometry-Only 3DGS, Dense Monocular SLAM	Beihang University	GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM	arXiv	paper
2026-07-05	LiDAR 3DGS SLAM, Geometry-Aware Covariance, Real-Time	Authors	Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling	arXiv	github
2026-07-02	Dynamic Gaussian SLAM, Dual-Level Probability, Semantic Map	Authors	DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability	arXiv	paper
2026-06-29	Task-Conditioned 3DGS, Real-Time Mapping, Multi-Agent Fusion	MIT	GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping	arXiv	paper
2026-06-29	RGB-Only Gaussian SLAM, Closed-Loop Geometry, Scale Feedback	CAS / USTC	MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM	IROS 2026	paper
2026-06-27	Object-Centric 3DGS, Lifelong Mapping, Dynamic Maintenance	Beijing Institute of Technology	CubifyGS: Object-Centric 3D Gaussian Splatting for Lifelong Dynamic Scene Maintenance	IROS 2026	paper
2026-03-10	Uncertainty-Aware 3DGS, RGB-D SLAM, Loop Detection	George Mason University	VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM	CVPR 2026	project / github
2025-11-20	Language-Embedded, Open-Vocabulary, 3DGS SLAM	KAIST	LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM	arXiv	paper
2025-07-25	Neural SLAM, Dense Mapping, Self-Supervised	Shanghai AI Lab	DINO-SLAM: Dense Tracking and Mapping with Self-Supervised Feature Learning	arXiv	paper
2025-07	Dynamic Surface, Non-Rigid, 4D Tracking	Imperial College	4DTAM: Dynamic Surface Gaussian SLAM	CVPR 2025	paper
2025-03-20	4DGS SLAM, Dynamic/Static, Tracking	Authors	4D Gaussian Splatting SLAM	ICCV 2025	paper / paper
2025-03-11	Gaussian SLAM, Dense Reconstruction, RGB-D	Zhejiang University	GigaSLAM: Gaussian Splatting-based Large-Scale Dense SLAM	arXiv	github
2025-03	Multi-Agent, 3DGS SLAM, Loop Closure	Authors	MAGiC-SLAM: Multi-Agent 3DGS SLAM	CVPR 2025	paper
2025-01-25	Gaussian SLAM, Dynamic Environments, Monocular	Stanford / ETH	WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments	CVPR 2025	project
2025-01-24	Multi-Robot, Semantic, Heterogeneous, 3DGS	Stanford	HAMMER: Heterogeneous, Multi-Robot Semantic Gaussian Splatting	RAL 2025	project
2024-11-03	Gaussian SLAM, Global BA, Monocular RGB	ETH / Meta	Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians	CVPR 2025	project
2024-09-10	Single-Image Calibration, Geometric Optimization	ETH / Meta	GeoCalib: Learning Single-image Calibration	ECCV 2024	paper
2024-04-11	Detector-Free SfM, Texture-Poor	Zhejiang Univ	Detector-Free Structure from Motion	CVPR 2024	github
2024-04	Pose Regression, Map-Relative, Multi-Scene, Highlight	Niantic / Oxford	Marepo: Map-Relative Pose Regression for Visual Re-Localization	CVPR 2024 Highlight	github
2024-02-20	Neural SLAM, Survey, Radiance Fields	TUM	How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey	arXiv	project
2023-12-11	Dense SLAM, Gaussian Splatting, RGB-D	TUM	Gaussian Splatting SLAM	CVPR 2024	github
2023-12-07	End-to-End SfM, Differentiable BA	Meta AI / Oxford	VGGSfM: Visual Geometry Grounded Deep SfM	CVPR 2024	github
2023-12-04	Gaussian SLAM, RGB-D, Volumetric	CMU / MIT	SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM	CVPR 2024	project / github
2021-12-22	Neural Mapping, Dense RGB-D SLAM, SDF	HKUST	NICE-SLAM: Neural Implicit Scalable Encoding for SLAM	CVPR 2022	project

🧱 2. 3D/4D Representation

This section focuses on the mathematical and data-structure layer used to represent geometry, appearance, and motion.

2.1 Explicit & Hybrid Representations

2.1.1 Structure-Aware 3D Gaussian Splatting

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-21	Gaussian Surfels, Topology Recovery, Mesh Extraction, Surface Reconstruction	University of Science and Technology of China	TopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction	arXiv	github
2026-08-20	Sparse Light Field, Casual Capture, 3D/4D Reconstruction, 3DGS	Cornell University	Sparse Light Field Sampling Improves Casual 3D and 4D Reconstruction	arXiv	project
2026-08-17	Pose-Free NVS, 3DGS Geometry, Visibility-Aware Guidance	Aalto University	SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis	arXiv	paper
2026-08-13	Feed-Forward 3DGS, 3D Anchors, Spatially Grounded Tokens	National University of Defense Technology	LocusGS: Spatially Grounded Tokens for Feed-Forward 3D Gaussian Splatting	arXiv	project
2026-08-03	Streaming Feed-Forward, Persistent Geometry, Memory-Bounded 3DGS	University of Science and Technology of China	StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting	arXiv	paper
2026-08-03	View-Conditioned, Feed-Forward 3DGS, Generalizable Reconstruction	Tsinghua University	UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction	arXiv	paper
2026-07-28	Dynamic 3DGS, Adaptive Streaming, Volumetric Video	Authors	SplatStream: Fine Granular Scalable Gaussian Splatting for Adaptive 3D Scene Streaming	arXiv	paper
2026-07-22	Feed-Forward 3DGS, Adaptive Tokens, Compact Representation	Yonsei University	ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion	arXiv	project
2026-04-16	Feed-Forward 3DGS, Global Scene Tokens, Compact	Tel Aviv University	GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens	arXiv	paper
2026-04-16	TokenGS, Learnable Gaussian Tokens, Pose-Robust	NVIDIA	TokenGS: Decoupling 3D Gaussian Prediction from Pixels	CVPR 2026 Highlight	project
2026-04-12	UniSplat, Unposed Multi-View, Feed-Forward	UC Berkeley	UniSplat: Learning 3D Representations from Unposed Multi-View Images	CVPR 2026	paper
2026-02-02	Feed-Forward 2DGS, Surface Continuity, Sparse Views	Shanghai Jiao Tong	SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors	ICLR 2026	paper
2025-07-31	Sparse-View 4D, Monocular Fusion, Cross-Video	Meta AI	MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion	ICCV 2025	paper
2025-06-17	Anti-Aliasing, Gaussian, 3D, Adaptive	CUHK	AAA-Gaussians: Anti-Aliasing 3D Gaussian Splatting	ICCV 2025	paper
2025-06-05	Feed-Forward 3DGS, Depth Parameterization, Geometry	Zhejiang University	Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting	3DV 2026	paper
2025-05-21	Sparse-View Surface, Geometry-Prioritized, 2DGS	Nankai Univ	Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views	CVPR 2025	paper
2025-04-03	Feed-Forward, No Camera, FreeSplatter	ZJU	FreeSplatter: Pose-Free 3DGS from Sparse Views	CVPR 2025	paper
2025-03-13	Few-Shot, Diffusion Prior, Repair + Inpainting	ZJU / Alibaba	RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors	ICCV 2025	paper
2025-01-11	Scene-Level, 3DGS, Open-Vocabulary, 4D LangSplat	UPenn	4D LangSplat: 4D Language Gaussian Splatting	CVPR 2025	paper
2024-12-09	Large-Scale Dynamic, City, 4DGS, Spotlight	ZJU	DynamicCity: Large-Scale 4D Gaussian City Modeling	ICLR 2025 Spotlight	paper
2024-09-26	Progressive, Pruning, 3DGS, CVPR	S-Lab	PUP 3D-GS: Progressive Pruning for 3DGS	CVPR 2025	paper
2024-03-26	2DGS, Surface Reconstruction, Geometry	TUM	2D Gaussian Splatting for Geometrically Accurate Radiance Fields	SIGGRAPH 2024	project
2024-03-21	Feed-Forward 3DGS, Sparse Views, Generalizable	Monash / Tübingen	MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images	ECCV 2024 Oral	project / github
2024-03-14	Multi-Scale, 3DGS, Level-of-Detail	Shanghai Jiao Tong	Multi-Scale 3DGS	CVPR 2024	paper
2023-12-19	Feed-Forward 3DGS, Image Pairs, Epipolar	MIT	pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction	CVPR 2024 Oral	github
2023-12-01	Distillation, Lightweight, 3DGS, Spotlight	Virginia Tech	LightGaussian: Distilled 3D Gaussian Splatting	NeurIPS 2024 Spotlight	paper
2023-11-30	3DGS, Structure, Sparse Views	USTC	SparseGS: Real-Time 360 Sparse View Synthesis using Gaussian Splatting	3DV 2025	project
2023-11-27	Anti-Aliasing, Mip, 3DGS, Best Student Paper	Inria	Mip-Splatting: Alias-free 3DGS	CVPR 2024 Oral / Best Student Paper	github
2023-11-27	Compression, Compact, 3DGS, Highlight	Tsinghua	Compact 3D Gaussian Splatting	CVPR 2024 Highlight	paper
2023-11-21	3DGS, Mesh Extraction, Surface	ETH Zurich	SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction	CVPR 2024	project
2023-08-08	3DGS, Real-Time Rendering, Explicit Radiance	Inria	3D Gaussian Splatting for Real-Time Radiance Field Rendering	SIGGRAPH 2023	github / paper

2.1.2 Voxel, Mesh & Point-Cloud Innovations

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-18	Sparse Voxel Latent, Fitting-Free 3DGS, Large-Area Generation	Amap, Alibaba	GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation	arXiv	paper
2026-07-22	Shape Completion, Unified 3D Representation, Faithful Geometry	Authors	Axolotl3D: A Unified Framework for Faithful 3D Shape Completion	arXiv	paper
2024-12-02	Structured Latent, 3D Generation, Mesh	Microsoft	TRELLIS: Structured 3D Latents for Scalable and Versatile 3D Generation	CVPR 2025	project / github
2024-03-04	Sparse Voxel, Text/Image-to-3D, Mesh	Stability AI	TripoSR: Fast 3D Object Reconstruction from a Single Image	arXiv	github
2022-12-16	Point Cloud, Diffusion, Shape Generation	OpenAI	Point-E: A System for Generating 3D Point Clouds from Complex Prompts	arXiv	github

2.2 Neural Implicit Representations

2.2.1 Advanced NeRF & SDF Architectures

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2025-07-15	Unbiased SDF, Neural Implicit Surface, SDF-to-Density	CUHK	UNIS: Unified Framework for Unbiased Neural Implicit Surfaces	ICCV 2025	paper
2024-09-06	α-NeuS, Alpha, SDF, Volume Rendering	ZJU	α-NeuS: Alpha-Governed Neural Implicit Surfaces	NeurIPS 2024	paper
2023-12-29	Objects as Volumes, NeRF, 3D Reconstruction, Oral	UPenn	Objects as Volumes: Feed-Forward 3D from a Single Image	CVPR 2024 Oral	paper
2023-04-13	Zip-NeRF, Anti-Aliasing, Mip, Grid	Google Research	Zip-NeRF: Anti-Aliased Grid-Based NeRF	ICCV 2023	project
2022-03-17	Tensor Factorization, Radiance Fields, Compression	Tsinghua	TensoRF: Tensorial Radiance Fields	ECCV 2022	project
2022-01-16	Hash Grid, Real-Time NeRF, Neural Graphics	NVIDIA	Instant Neural Graphics Primitives with a Multiresolution Hash Encoding	SIGGRAPH 2022	github / paper
2021-12-15	EG3D, Triplane, 3D GAN, Generative	NVIDIA	EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks	CVPR 2022 Oral	github
2021-12-09	Plenoxels, No Neural Network, Fast, Oral	UC Berkeley	Plenoxels: Radiance Fields without Neural Networks	CVPR 2022 Oral	github
2021-12-07	Ref-NeRF, Reflection, Specular, Best Student Paper HM	Google Research	Ref-NeRF: Structured View-Dependent Appearance for NeRF	CVPR 2022 Best Student Paper HM	project
2021-11-23	Unbounded Scenes, Anti-Aliasing, NeRF	Google Research	Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields	CVPR 2022	project
2021-06-20	SDF, Surface Reconstruction, Neural Rendering	MPI-IS	NeuS: Learning Neural Implicit Surfaces by Volume Rendering	NeurIPS 2021	project
2021-04-13	BARF, Bundle-Adjusting NeRF, Oral	UC Berkeley	BARF: Bundle-Adjusting Neural Radiance Fields	ICCV 2021 Oral	github
2020-08-05	NeRF-W, Unbounded, In-the-Wild	Google Research	NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections	CVPR 2021	github
2020-03-19	NeRF, View Synthesis, Neural Rendering	UC Berkeley	NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis	ECCV 2020	github / paper

2.3 Dynamic & Spatiotemporal 4D

2.3.1 4D Gaussian Splatting (4DGS)

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-23	Dynamic 3DGS, Gradient Decoupling, Novel View Synthesis	Authors	GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis	arXiv	paper
2026-06-22	Dynamic 3DGS, Visibility-Aware Densification, Temporal Lifespan	Indian Institute of Science	Temporally Aware Densification for Dynamic 3D Gaussian Splatting	arXiv	paper
2025-07	7DGS, Spatial-Temporal-Angular, Unified	Authors	7D Gaussian Splatting: Unified Spatial-Temporal-Angular GS	ICCV 2025	paper
2024-10	Event Camera, High-Speed, 4D, STD-GS	Authors	STD-GS: SpatioTemporal-Disentangled Gaussian Splatting with Event Cameras	ICCV 2025	paper
2023-10-12	4DGS, Dynamic Scenes, Real-Time Rendering	Zhejiang University	4D Gaussian Splatting for Real-Time Dynamic Scene Rendering	CVPR 2024	project
2023-08-18	Dynamic 3DGS, Scene Motion, Multi-View Video	Cornell	Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis	3DV 2025	github / paper
2023-01-24	K-Planes, Explicit, 4D, Space-Time	Authors	K-Planes: Explicit Radiance Fields in Space, Time, and Appearance	CVPR 2023	github
2023-01-23	HexPlane, 4D Representation, Space-Time	CMU	HexPlane: A Fast Representation for Dynamic Scenes	CVPR 2023	project
2021-06-24	Dynamic NeRF, Deformation, Canonical Space	Google Research	HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields	SIGGRAPH Asia 2021	project

2.3.2 Deformation Graphs & Canonical Spaces

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-24	Structured Motion, SE(3), 4D Reconstruction	Tsinghua University	SM4RT: Learning Structured Motion Geometry for 4D Reconstruction	arXiv	project / paper
2023-12-04	Deformation, Dynamic Radiance Fields, Canonical	ETH Zurich	SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes	CVPR 2024	project
2023-06-05	Non-Rigid Tracking, Neural Deformation, 4D	Tsinghua	Neuralangelo: High-Fidelity Neural Surface Reconstruction	CVPR 2023	project

🏗️ 3. 3D Reconstruction

Reconstruction systems recover objects or scenes from images, video, RGB-D, or multi-sensor streams under offline, online, and dynamic conditions.

3.1 Static Reconstruction

3.1.1 Object-Centric Reconstruction

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-08	Active In-Hand Reconstruction, Uncertainty, Next-Best View	ShanghaiTech University	AURORA: Active Uncertainty-Driven Re-Orientation for In-Hand Reconstruction	CoRL 2026	project
2026-07-21	Single-View 3D, Object Perception, Generative Reconstruction	Deakin University	Seeing Before Generating: Object Perception Enhances Single-View 3D Reconstruction	arXiv	project
2026-06-17	Sparse-View Object, Flow Steering, 3DGS Refinement	Graz University of Technology	FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity	arXiv	project
2026-05-05	Generative Reconstruction, Multi-View Alignment, Pose	Tsinghua	Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation	arXiv	project
2025-11-19	Single Image, Object Mesh, SAM 3D	Meta AI	SAM 3D Objects	GitHub	github
2025-10-23	Pose-Free Online, Free-Moving Objects, Constant Memory	SUTD	OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects	NeurIPS 2025 Spotlight	project
2025-06-05	RGB-D Object Completion, Novel Depth, Feed-Forward	Carnegie Mellon University	RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion	NeurIPS 2025	project
2025-06	Feed-Forward, Densification, Gaussian, Detail	Authors	Generative Densification: Feed-Forward 3DGS Densification	CVPR 2025	paper
2025-06	Photogrammetry Foundation, Multi-Task, Highlight	Authors	Matrix3D: A Foundation Model for Photogrammetry	CVPR 2025 Highlight	paper
2025-04-04	Sparse-View, Feed-Forward, Camera, Geometry	Ant Research / Stanford	FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views	CVPR 2025	project
2024-07	Ego-Centric, Autonomous Driving, Sparse-View	Authors	Omni-Scene: Omni-Gaussian for Ego-Centric Sparse-View Reconstruction	CVPR 2025	paper
2024-06-14	Multi-View, Stereo, Feed-Forward	NAVER Labs	MASt3R: Grounding Image Matching in 3D with MASt3R	ECCV 2024	project / github
2023-12-21	Multi-View, Pointmap, Pose-Free	NAVER Labs	DUSt3R: Geometric 3D Vision Made Easy	CVPR 2024	project / github
2023-12-13	Object Pose, Reconstruction, Model-Based	NVIDIA	FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects	CVPR 2024	project
2023-03-24	Unknown Object, RGB-D, 6-DoF Tracking, Neural SDF	NVIDIA	BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects	CVPR 2023	project / github

3.1.2 Large-Scale Scene Reconstruction

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-08	Feed-Forward, Compositional Scene, Complete Meshes, Simulation-Ready	University of Illinois Urbana-Champaign	FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute	arXiv	project / github
2026-09-04	Bundle Adjustment, Multi-View Matching, Monocular Priors, Online+Offline	NAVER Labs Europe	BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors	ECCV 2026	paper
2026-08-31	Real-to-Sim, Parse-Generate-Place, Composable Object Assets	ByteDance Seed	Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling	arXiv	project
2026-08-25	Single Image, Generative Reconstruction, Complete Object Assets, Scene Assembly	Huawei	SceneReGen: Generative Reconstruction of 3D Scenes from a Single Image	arXiv	paper
2026-08-18	Instance-Grouped 3DGS, Semantic Reconstruction, Referential Scene Graph	Shanghai Jiao Tong University	GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting	arXiv	paper
2026-08-18	Generative NVS, Reconstruction/Generation Split, Scene Coordinates	KAIST	GenRec: Knowing Where to Reconstruct and Where to Generate	arXiv	project
2026-08-18	Long Sequence, Chunk Priors, Sim(3) Assembly, Test-Time Adaptation	Kosmo Research	GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly	arXiv	project
2026-08-15	Long Sequence, Scale-Consistent Alignment, Test-Time Adaptation	Northwestern Polytechnical University	VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction	ACM Multimedia 2026	github
2026-08-12	Streaming Multi-View, Metric 3D, Feed-Forward Prior, Object Detection	ETH Zurich	Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs	ECCV 2026	project
2026-08-07	Sparse View, Editable Indoor Scenes, Executable Scene Programs	City University of Hong Kong	Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs	arXiv	paper
2026-07-31	Active Reconstruction, Next-Best-View, Predictive Entropy	Fudan University	GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction	arXiv	paper
2026-07-23	Underwater 3D, Feed-Forward Reconstruction, Degradation Adaptation	HKUST	WAT3R: Feedforward Underwater 3D Reconstruction	arXiv	project
2026-07-15	Feed-Forward Driving Reconstruction, Layered 3DGS, Dynamic Actors	NVIDIA	Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation	arXiv	project / github / docs
2026-07-10	3D Foundation Model, Global SfM, Bundle Adjustment	HKUST	Glob3R: Global Structure-from-Motion with 3D Foundation Models	arXiv	project
2026-07-08	Feed-Forward 3D, Unposed Images, Drift-Robust	Authors	NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction	ECCV 2026	paper
2026-06-09	RGB-T, Thermal Geometry, Low-Light	University of Minnesota	DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax	arXiv	project
2026-06-02	Single Image, Physics-in-the-Loop, Simulation-Ready	Seoul National University	SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image	arXiv	project
2026-05-14	VGGT, Scaling, Static+Dynamic	University of Oxford	VGGT-Omega: Scaling VGGT to Large-Scale 3D Reconstruction	CVPR 2026 Oral	project / github / demo / model
2026-05-07	Feed-Forward 3D, Token Reduction, Long Sequence	Peking University	Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction	arXiv	paper
2026-04-30	Generalizable, Sparse-View, Unposed Images, Outdoor	UIUC / NVIDIA	GenWildSplat: Generalizable Sparse-View 3D Reconstruction from Unconstrained Images	arXiv	paper
2026-03-24	Panoramic Video, Pose-Free 3DGS, Consistent Depth Prior	University of Chinese Academy of Sciences	Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors	CVPR 2026	github
2026-03-16	Event-to-Edge, Pose-Free, Gaussian Reconstruction	KAIST	E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction	CVPR 2026	paper
2026-02-26	VGGT, TTT, Large-Scale	NVIDIA	VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale	CVPR 2026	project
2026-02-03	Single Image, Object Decomposition, Occlusion-Aware Scene Reconstruction	University of California, San Diego	Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal	3DV 2026	project
2025-09-24	Mirror Stereo, Single-View 3D, Symmetry Constraint	University of Oxford	Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections	3DV 2026	project / github / dataset
2025-09-16	Universal 3D, Metric Reconstruction, Optional Priors	Meta AI	MapAnything: Universal Feed-Forward Metric 3D Reconstruction	3DV 2026	project
2025-08-05	Unposed Multi-View, 3DGS, Semantic Reconstruction	Sungkyunkwan University	Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images	CVPR 2026	paper
2025-07-17	Permutation-Equivariant, Visual Geometry, Point Maps	Oxford / Meta	π³: Permutation-Equivariant Visual Geometry Learning	ICLR 2026	github
2025-07	Monocular Prior, MVS, DTU/Tanks SOTA	Authors	MonoMVSNet: Monocular Prior Guided MVS	ICCV 2025	paper
2025-07	Latent Align, Stereo+Monocular, Highlight	Authors	BridgeDepth: Unified Monocular and Stereo Depth	ICCV 2025 Highlight	paper
2025-06-30	Video-Depth Augmentation, Scalable Training, Feed-Forward 3D	Australian National University	Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction	NeurIPS 2025	project
2025-06-03	Monocular Depth, Dynamic Video, Alignment	HKUST / CUHK / HKU	Align3R: Aligned Monocular Depth Estimation for Dynamic Videos	CVPR 2025	github
2025-06	Aerial-Ground, Large-Scale, 3DGS	Authors	Horizon-GS: Unified Aerial-Ground 3DGS	CVPR 2025	paper
2025-06	Autonomous Driving, Feed-Forward, 3DGS	Authors	EVolSplat: Feed-Forward 3DGS for Urban Driving	CVPR 2025	paper
2025-06	Sparse-View, Super-Resolution, 3DGS	Authors	S2Gaussian: Sparse-View Super-Resolution 3DGS	CVPR 2025	paper
2025-05-05	Relative Camera Pose, Regression, Localization	Aalto / HKU	Reloc3r: Large-Scale Training of Relative Camera Pose Regression	CVPR 2025	github
2025-03-28	Feed-Forward, Surface, MVS, Multi-View	Authors	MVSAnywhere: Zero-Shot Multi-View Stereo	CVPR 2025	paper / paper
2025-03-17	Feed-Forward, Multi-View, Auxiliary Priors	ETH / Microsoft	Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors	CVPR 2025	project
2025-03-14	Feed-Forward 3D, Pose-Free, Point Map	Meta AI	VGGT: Visual Geometry Grounded Transformer	CVPR 2025 Best Paper	project / github
2025-03-03	Multi-View, Symmetric, 1000+ Images, O(N)	NAVER Labs	MUSt3R: Multi-view Network for Stereo 3D Reconstruction	CVPR 2025	project
2025-01-23	Feed-Forward, 1500+ Images, 251 FPS	Meta AI	Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass	CVPR 2025	project
2024-12-12	Feed-Forward, Online, Dense, Monocular	Shanghai AI Lab / PKU	SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos	CVPR 2025 Highlight	project
2024-12-09	Sparse View, Single-Stage, 2 Seconds	Meta AI	MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds	CVPR 2025 Oral	project
2024-09-27	Multi-View Reconstruction, Matching, MVS	NAVER Labs	MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion	3DV 2025	github
2024-08-28	Spatial Memory, Feed-Forward, Multi-View	HKU	Spann3R: 3D Reconstruction with Spatial Memory	3DV 2025 Oral (Best Paper Candidate)	project

3.2 Streaming & Online Reconstruction

3.2.1 Dense Semantic/Instance Mapping

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-07	Online SLAM, Functional Scene Graph, Interaction Elements, Map Memory	Tsinghua University	Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs	arXiv	github
2026-09-01	Training-Free, Open-Vocabulary Instance Map, RGB-D/Monocular SLAM	University of Technology Sydney	VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM	arXiv	paper
2026-08-24	Spatio-Temporal SLAM, Open-Vocabulary, 4D Scene Graph, VLN	Carnegie Mellon University	SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation	arXiv	project
2026-08-18	Open-Vocabulary Map, Instance Preservation, Fine-Grained Retrieval, Target Absence	Xi'an Jiaotong University	OVIP-SG: Open-Vocabulary Instance-Preserving Scene Graphs for Mapping and Retrieval of Small, Fine-Grained Objects	arXiv	github
2026-06-23	Object-Level Map, Open-Vocabulary, Relocalization	Zhejiang University	Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization	arXiv	paper
2026-05-05	Online, Voxel+Instance, Open-Vocabulary Mapping	Örebro University	FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping	arXiv	project
2026-05-03	Gaussian-Language Map, Zero-Shot Navigation, Multi-Scale	CASIA	Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning	arXiv	github
2026-03-04	Semantic 3DGS, Online, CLIP, Open-Vocabulary	National University of Singapore	EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding	CVPR 2026	project
2025-08-02	Open-Vocabulary, Hybrid 3DGS+TSDF, Dense Mapping	Tsinghua	OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting	arXiv	project
2025-07	Feed-Forward, Panoramic Segmentation, DUSt3R	Authors	PanSt3R: Single-Feed 3D and Panoptic Segmentation	ICCV 2025	paper
2023-10-05	Open-Vocabulary, RGB-D, TSDF, Real-Time Mapping	University of Arkansas	Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation	IROS 2024	project / github
2023-02-14	Open-Set, Multimodal, 3D Map, Language Query	MIT	ConceptFusion: Open-set Multimodal 3D Mapping	ICRA 2023	project / github
2022-10-11	Implicit Field, CLIP, Semantic Search, Robot Memory	New York University	CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory	ICRA 2023	project

3.2.2 Continuous Neural Tracking & Mapping

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-03	Online 3R, Multi-Relative Pose Query, Pose-Graph Optimization	National Yang Ming Chiao Tung University	Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction	ECCV 2026	project
2026-09-01	Online Feed-Forward 3R, Unordered UAV Images, Retrieval+Retry	Wuhan University	On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios	arXiv	github
2026-08-03	Active Reconstruction, Ergodic Coverage, Trajectory Optimization	Johns Hopkins University	TRACE: Ergodic Trajectory Optimization for Active Scene Reconstruction	arXiv	github
2026-08-03	Feed-Forward SLAM, Sim(3) Factor Graph, Persistent Mapping	Ulsan National Institute of Science and Technology	UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization	ECCV 2026	project
2026-07-25	Semantic SLAM, Data Association, Object Landmarks	MIT	Semantic Semi-Incremental Data-Association-Free Object SLAM	arXiv	paper
2026-07-23	Gaussian SLAM, Large-Scale Mapping, Real-Time	Athena Research Center	GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition	IROS 2026	github
2026-07-16	Multi-Agent 3R, RGB Video, Point-Map Fusion	University of Bologna	MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos	arXiv	project
2026-07-16	Incremental 3DGS, Unordered Capture, Global Consistency	Inria	Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency	SIGGRAPH 2026	paper
2026-07-01	Long-Sequence, Instance Anchors, Persistent Spatial Memory	Beijing Jiaotong University	LIST3R: Long-sequence Instance-aware 3D Reconstruction	arXiv	project
2026-06-23	3DGS-SLAM, Memory-Efficient, Outdoor Mapping	University of Minnesota	Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM	ICRA 2026	github
2026-06-20	RGB+Pose, 3DGS Scene Regression, Robot Capture	Peking University	ACEsplat: Accelerated 3D Gaussian Scene Regression via RGB and Poses Only	arXiv	paper
2026-06-19	3DGS-SLAM, Degeneracy-Robust, Real-Time Tracking	Nanyang Technological University	Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM	IROS 2026	paper
2026-06-18	LiDAR-Inertial-Thermal, 3DGS Mapping, Illumination-Robust	Shenzhen University	LIT-GS: LiDAR-Inertial-Thermal Gaussian Splatting for Illumination-Robust Mapping	IROS 2026	paper
2026-06-03	Streaming, Transient Anchors, Long-Horizon Mapping	Authors	Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping	arXiv	paper
2026-06	Spatial-Difference Sensor, Edge-Guided Tracking, 3DGS	Tsinghua University	SDGS: Spatial Difference Guided Gaussian Splatting for Simultaneous Localization and 3D Reconstruction	CVPR 2026	paper
2026-06	Stereo 3DGS-SLAM, Auto-Exposure Robustness, Photometric Mapping	South China University of Technology	AERGS-SLAM: Auto-Exposure-Robust Stereo 3D Gaussian Splatting SLAM	CVPR 2026	github
2026-05-10	VGGT, Retrieval, Constant Memory	Fudan University	RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval	arXiv	github
2026-04-24	4DGS-SLAM, Optical Flow, Dynamic Mapping	National University of Singapore	Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM	CVPR 2026	github
2026-04-15	Streaming, Feed-Forward, Long Video	Robbyant	LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction	arXiv	github
2026-02-13	Streaming, Autoregressive, Long Sequence	3DAgentWorld	LongStream: Long-Sequence Streaming Autoregressive Visual Geometry	CVPR 2026	project
2026-01-03	StreamVGGT, KV Cache, Memory Compression	Sun Yat-sen University	XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer	arXiv	github
2025-09-30	TTT, Online, Long Context	Shanghai AI Lab	TTT3R: 3D Reconstruction as Test-Time Training	arXiv	project
2025-08-14	Streaming, Causal Transformer, Sequential	NTU / Shanghai AI Lab	STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer	arXiv	project
2025-01-21	Online 3D, Recurrent Pointmap, Streaming	Meta AI	CUT3R: Continuous 3D Perception Model with Persistent State	CVPR 2025 Oral	project / github
2024-12-16	MASt3R, Dense SLAM, Real-Time	Imperial College London	MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors	CVPR 2025	github
2023-09-05	Global BA, Neural Implicit, Dense RGB-D SLAM	University of Bologna	GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction	ICCV 2023	project / github
2022-11-21	Hybrid SDF, Dense RGB-D SLAM, Keyframes	Idiap Research Institute	ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields	CVPR 2023	project / github
2021-08-24	Deep SLAM, Dense BA, Monocular/Stereo/RGB-D	Princeton University	DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras	NeurIPS 2021	github
2021-03-23	Neural Implicit, Online RGB-D, Dense SLAM	Imperial College London	iMAP: Implicit Mapping and Positioning in Real-Time	ICCV 2021	project / github

3.3 Dynamic 3D Reconstruction

3.3.1 Non-Rigid Tracking & Reconstruction

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-08	Long-Range 4D Motion, 3D Queries, Occlusion-Robust Trajectory Chaining	Carnegie Mellon University	Point4D: Long-range 4D Motion Reconstruction	arXiv	project
2026-09-08	Event Stream, Extreme-Low-Frame-Rate RGB, Dynamic 3DGS, Real-Time	Macau University of Science and Technology	EdMCGS: Event-Driven Markov Chain Gaussian Splatting for Extreme-Low-Frame-Rate Dynamic Scene Reconstruction	Neurocomputing	github+dataset
2026-09-05	Sparse-View 4D, Spatio-Temporal Depth Alignment, Dynamic 3DGS	BIGAI	UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignment	ECCV 2026	project
2026-08-18	Query-Conditioned 4D, Scene Flow, Dynamic Points, Sparse-to-Dense	Kosmo Research	UniQuery4R: Unified 4D Scene Reconstruction from a Single Query	arXiv	project
2026-07-29	Articulated Objects, Structure-aware 3DGS, Part Connectivity	POSTECH	StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction	arXiv	paper
2026-07-21	Streaming 4D, Instance Grounding, Geometry Transformer	Horizon Robotics	IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer	arXiv	project
2026-07-16	Online Dynamic NVS, Space-Time Memory, Real-Time	University of Washington	Online Neural Space Time Memory for Dynamic Novel View Synthesis	arXiv	project
2026-07-01	Dynamic Gaussian Reconstruction, Monocular Video, Generative	Stanford University	World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video	arXiv	project
2026-06-23	Articulated Digital Twin, RGB-D, URDF Export	ETH Zurich	ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D Videos	ICRA 2026 Workshop	paper
2026-06-22	Monocular Video, 4DGS, In-the-Wild Non-Rigid	Carnegie Mellon University	Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild	arXiv	project
2026-06-22	Dynamic Driving, Sparse Voxels, LiDAR-Guided	Huawei Paris Research Center	DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction	arXiv	paper
2026-06-09	Future Extrapolation, 4DGS, Autonomous Driving	Tsinghua University	Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving	arXiv	project
2026-06-09	Manipulation Video, Decoupled 3DGS, Scene Graph	Authors	ManiSplat: Manipulation Trajectory Synthesis from Monocular Video via Decoupled 3D Gaussian Splatting	arXiv	paper
2026-06-02	Object Permanence, Differentiable Physics, 4DGS	Authors	PersistGS: Differentiable Physics for Object Permanence in 4D Gaussian Splatting	CVPR 2026 Workshop	paper
2026-06	Single Event Camera, Deformable 3DGS, High-Speed 4D	ShanghaiTech University	FastEventDGS: Deformable Gaussian Splatting for Fast Dynamic Scenes from a Single Event Camera	CVPR 2026	paper
2026-04-10	Feed-Forward, Unconstrained Views, Semantic-Geometry	Nanyang Tech	FF3R: Feedforward Feature 3D Reconstruction from Unconstrained Views	CVPR 2026 Findings	paper
2026-04-10	Dynamic 4D, Semantic Prior, Gaussian SLAM, Action-Control	University of Zurich	Genie 4D: Semantic-Prior-Guided 4D Dynamic Scene Reconstruction	arXiv	paper
2026-04-10	Dynamic/Static Disentanglement, Uncertainty-Aware, Feed-Forward	Zhejiang University	Robust 4D VGT: Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors	arXiv	paper
2026-04-07	Functional Scenes, Egocentric Interaction, URDF/USD	Stanford	FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos	CVPR 2026	paper
2026-04-05	Sparse Camera, 4DGS, Neural Decay, CVPR 2026	Authors	4C4D: 4 Camera 4D Gaussian Splatting	CVPR 2026	paper / paper
2026-03-30	Dynamic Surface, Explicit Geometry, High Fidelity	Australian National University	4DSurf: High-Fidelity Dynamic Scene Surface Reconstruction	CVPR 2026	paper
2026-03-21	RayMap, Dynamic, Streaming	University of Illinois Chicago	RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction	arXiv	project / github
2026-03-09	Dynamic VGGT, Autonomous Driving, 4D	Fudan University	DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving	arXiv	paper
2025-11-23	Dynamic Geometry, Spatiotemporal, VGGT	Huazhong University of Science and Technology	4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation	arXiv	paper
2025-11-07	Motion-Aware, Monocular Video, Bundle Adjustment	KAIST	4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes	NeurIPS 2025	paper
2025-10-20	VGGT-4D, Pose/Geometry, Dynamic Mask	Harvard	PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception	ICLR 2026	project
2025-08-13	3D Reconstruction, Human Motion, Video	Shanghai AI Lab	Human3R: Reconstructing 3D Human Avatars from Monocular Video	CVPR 2025	project
2025-07	Human, Multi-View, Sparse, Robust, RoGSplat	Authors	RoGSplat: Robust Generalizable Human Gaussian Splatting	CVPR 2025	paper
2025-06-11	Dynamic Human, Temporal Consistency, 4D	Tsinghua	CARI4D: Cross-Modal Alignment and Reconstruction for Interactive 4D Human	CVPR 2025	project
2025-06-10	Online, Dynamic 3DGS, Uncalibrated Video	University of British Columbia	StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams	ICLR 2026	project / github
2025-06-09	4DGS, Transformer, Monocular Video	Meta Reality Labs	4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos	NeurIPS 2025 Spotlight	project
2025-06-02	Video Generators, 4D Geometry	Oxford VGG / NAVER LABS	Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction	ICCV 2025 Highlight	paper
2025-06	Self-Supervised, Dynamic, Driving, Flow	Authors	SplatFlow: Self-Supervised Dynamic 3DGS with Neural Motion Flow	CVPR 2025	paper
2025-06	Few-Shot, Personal Avatar, Highlight	Authors	FRESA: Personalized 3D Human Avatar from Few Images	CVPR 2025 Highlight	paper
2025-06	Real-Time Avatar, 166fps, Gaussian, Highlight	Authors	MMLP-Human: Real-Time High-Fidelity Gaussian Human Avatar	CVPR 2025 Highlight	paper
2025-05-27	4D, Dual Correspondences, Dynamic Video	NUS / Shanghai AI Lab	C4D: 4D Made from 3D through Dual Correspondences	ICCV 2025	project
2025-05-14	4D Pointmaps, Dynamic-Static Disentanglement	KAIST / ETH / Sony	D2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes	NeurIPS 2025	project
2025-05-02	Training-Free, Motion Disentangle, DUSt3R	Westlake / MPI	Easi3R: Estimating Disentangled Motion from DUSt3R Without Training	ICCV 2025	project
2025-04-17	4D Tracking, Feed-Forward, Pointmap, Tracking	MPI / UC Berkeley	St4RTrack: Simultaneous 4D Reconstruction and Tracking	ICCV 2025	paper / paper
2025-04-07	Neural Rendering, Human, No Eyes	University of Cambridge	Seeing Without Eyes: Neural Human Rendering from Monocular Video	CVPR 2025	project
2025-03-24	Multi-Object, 4D, In-the-Wild Videos	CMU	GenMOJO: Robust Multi-Object 4D Generation for In-the-wild Videos	CVPR 2025	project
2025-02-27	Layered Avatar, Hair, Face, Meta	Authors	LUCAS: Layered Universal Codec Avatars	CVPR 2025	paper / paper
2025-01-22	3D Reconstruction, Canonical, Multi-View	Stanford	UniCon3R: Unified 3D Reconstruction and Recognition	CVPR 2025	project
2024-12-03	Single Image, Animatable, Avatar, 4DGS	Authors	AniGS: Animatable Gaussian Avatar from a Single Image	CVPR 2025	paper / paper
2024-11-27	4D Generation, Multi-View Video, Diffusion	Google	CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models	CVPR 2025	project
2024-10-28	Dynamic Geometry, DUSt3R, Motion	University of Oxford	MonST3R: Estimating Geometry in the Presence of Motion	ICLR 2025	project / github

3.3.2 Deformation Graphs & Canonical Spaces

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-02-12	4D Dynamic, Monocular Video, Tree-Chains	Cornell	WorldTree: Towards 4D Dynamic Worlds from Monocular Video using Tree-Chains	ICLR 2026	paper
2025-11-01	4D Scene, Feed-Forward, Controllable, Video Diffusion	Shanghai AI Lab	Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models	CVPR 2026	paper
2025-10-15	Dynamic 4D, Gaussian, Canonical	Zhejiang University	Director: Directed Generative Models for 4D Scene Evolution	CVPR 2025	project
2025-08-06	Multi-Baseline, Generalizable, Gaussian	Authors	MuGS: Multi-Baseline Generalizable Gaussian Splatting	ICCV 2025	paper / paper
2025-07	Surface, Gaussian Surfels, 2DGS, Sparse-View, Spotlight	Authors	MAtCha Gaussians: Atlas Charting with 2D Gaussian Surfels	CVPR 2025 Spotlight	paper
2025-07	SDF+3DGS, Hybrid, Surface, ICCV	Authors	SurfaceSplat: SDF+3DGS Hybrid Surface Reconstruction	ICCV 2025	paper
2025-07	Sparse-View, Implicit, Voxel, Consistency	Authors	SparseRecon: Sparse-View Implicit Surface Reconstruction	ICCV 2025	paper
2025-07	Low-Texture, Reflection, Unified, +21%	Authors	HiNeuS: Unified Neural Implicit Surface Reconstruction	ICCV 2025	paper
2025-06	Joint Human+Scene, MASt3R Extension	Authors	HAMSt3R: Joint Human and Scene 3D Reconstruction	ICCV 2025	paper
2024-11-20	4D Reconstruction, Gaussian Splatting, Forward	Shanghai AI Lab	Forge4D: Gaussian Splatting for Forward Facing 4D Reconstruction	arXiv	paper

🎛️ 4. 3D Generation

This section tracks methods that create new 3D assets, parts, articulated objects, scenes, and editable 3D worlds, with emphasis on physical and simulation use.

4.1 Object-Level Generation

4.1.1 Image/Text to 3D Mesh

Single Image / Text-Conditioned Object Mesh

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-10	Multi-View, Reconstruction Prior, Noise Inversion, Faithful Asset Completion	HKUST	ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation	arXiv	paper
2026-09-09	Image-to-3D, Partial Geometry, Test-Time Guidance, SAM 3D	University of Oxford	Guiding Image-to-3D Generation with Test-Time Partial Observations	arXiv	paper
2026-07-22	Code-Native, Programmable, 3D Assets	Authors	Nova3D: Code-Native Generation of Programmable 3D Assets	arXiv	paper
2026-06-23	Image-to-3DGS, Sparse Voxel, High-Fidelity Assets	The Australian National University	FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation	arXiv	paper
2026-06-23	Vehicle Assets, 3D-Consistent Views, Simulation	Shanghai Jiao Tong University	3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis	arXiv	paper
2026-06-22	Constraint Meshes, Controllable Assets, TRELLIS	University of Tübingen	Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation	arXiv	project
2026-05-22	Image-to-3D, Deployable Mesh, UV, Real-Time	Meta Reality Labs	AssetGen: Deployable 3D Asset Generation at Interactive Speed	arXiv	paper
2026-05-11	Pixel-Aligned, Image-to-3D, PBR, Multi-View	Tencent ARC	Pixal3D: Pixel-Aligned 3D Generation from Images	SIGGRAPH 2026	project / github / demo
2026-05-01	Pose-Aware, Diffusion, 3D Geometry, Direct	Renmin University	PAD: Pose-Aware Diffusion for 3D Generation	arXiv	paper
2026-04-22	Simulation-Ready, PBR, Part-Aware, Articulation	ByteDance Seed	Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation	arXiv	demo
2025-12-16	Image-to-3D, O-Voxel, PBR Materials	Microsoft	Native and Compact Structured Latents for 3D Generation	arXiv	github / model
2025-11-20	Single Image, Multi-Object, Layout, SAM 3D	Meta AI	SAM 3D: 3Dfy Anything in Images	arXiv	github
2025-10-23	Single Image, Pose-Grounded, Flow Matching	Meta AI	CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling	arXiv	project
2025-10-09	PBR, Material Diffusion, Relighting, Single Image	Stability AI	SViM3D: Stable Video Material Diffusion for Single Image 3D Generation	arXiv	paper
2025-06-18	Image-to-3D, PBR Materials, Production Assets	Tencent	Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material	arXiv	github / model
2025-05-23	Gigascale 3D, Sparse Volume, Image Conditioning	Nanjing University	Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention	NeurIPS 2025	project / github
2025-05-12	Textured Assets, Controllable 3D, Open Framework	StepFun	Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets	arXiv	github
2025-05-07	Image-to-3D, PBR Textured Mesh, Render-Enhanced Auto-Encoder	Tsinghua	MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation	CVPR 2025	project
2025-03-28	Geometry Detail, Normal Bridging, Image-to-3D	Cornell	Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging	arXiv	project
2025-03-03	Text/Image-to-3D, Bundle Image, Data-Efficient (147K)	HKUST(GZ)	Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation	arXiv	github
2025-02-10	Shape Synthesis, Rectified Flow, Image-to-3D	VAST AI / Tripo	TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models	arXiv	github / model
2025-01-21	Image/Text-to-3D, Mesh, Texture	Tencent	Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation	arXiv	github
2025-01-08	Point-Aware, Interactive Editing, Single Image	Stability AI / UIUC	SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images	arXiv	project / model
2024-11-11	Text/Image-to-3D, PBR, Multi-View Diffusion	NVIDIA	Edify 3D: Scalable High-Quality 3D Asset Generation	arXiv	project
2024-09-19	3DTopia-XL, Primitive Diffusion, Large Scale, Highlight	NTU / PKU	3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion	CVPR 2025 Highlight	project
2024-08-01	Fast Mesh, UV Unwrap, Material Disentanglement	Stability AI	Stable Fast 3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement	arXiv	project / github
2024-07-02	Text-to-Mesh, PBR, Geometry+Texture	Meta	Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials	NeurIPS 2024	project / paper
2024-06-26	GaussianDreamer, Text-to-3DGS, 2D+3D Diffusion	HUST	GaussianDreamer: Fast Generation from Text to 3D Gaussians	CVPR 2024	github
2024-05-30	High-Quality Mesh, Multi-View Normals, ISOMER	Tsinghua	Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image	arXiv	project
2024-05-23	Text-to-3D, 3D-DiT, Interactive Refinement	HKUST	CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner	arXiv	github
2024-05-19	Multi-View Diffusion, Row-Wise Attention, Mesh	University of Hong Kong	Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention	arXiv	project
2024-04-10	Single Image, Sparse-View LRM, Mesh	Tencent ARC	InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models	arXiv	github
2024-03-18	Single Image, Orbital Video, Multi-View Prior	Stability AI	SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion	arXiv	project
2024-03-08	Textured Mesh, Convolutional Reconstruction, Single Image	Shanghai AI Lab	CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model	arXiv	project
2024-03-04	3DTopia, Hybrid Diffusion, Text-to-3D	NTU / PKU	3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors	CVPR 2024	project
2024-02-20	MVDiffusion++, Dense High-Res, Sparse-View	Simon Fraser / Meta	MVDiffusion++: A Dense High-Resolution Multi-view Diffusion Model	ECCV 2024	paper
2024-02-07	Multi-View Gaussian, Fast 3D Content, Image/Text	Peking University	LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation	ECCV 2024 Oral	github
2023-12-06	XCube, Sparse Voxel, Large-Scale, Highlight	NVIDIA	XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies	CVPR 2024 Highlight	project
2023-12-05	ReconFusion, Diffusion Prior, 3D Reconstruction	Columbia / Google	ReconFusion: 3D Reconstruction with Diffusion Priors	CVPR 2024	paper
2023-11-27	MeshGPT, Triangle Mesh, Decoder-Only, Transformer	TUM	MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers	CVPR 2024	project
2023-11-19	LucidDreamer, Interval Score, Text-to-3D, Highlight	HKUST(GZ)	LucidDreamer: Towards High-Fidelity Text-to-3D via Interval Score Matching	CVPR 2024 Highlight	project
2023-11-15	DMV3D, Multi-View Diffusion, 3D LRM, NeRF	Adobe / Stanford	DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model	NeurIPS 2023	paper
2023-10-26	MVDiffusion, Multi-View, Consistent, Single Image	Simon Fraser	MVDiffusion: Multi-view Consistent Image Generation from a Single Image	CVPR 2024	github
2023-10-25	DreamCraft3D, Bootstrapped, Hierarchical, 3D	DeepSeek / Tsinghua	DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior	ICLR 2024	project
2023-10-23	Cross-Domain Diffusion, Multi-View Normals, Mesh	HKUST	Wonder3D: Single Image to 3D using Cross-Domain Diffusion	CVPR 2024 Highlight	github
2023-10-23	Single Image, Consistent Multi-View Diffusion	UC San Diego	Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model	arXiv	github
2023-09-28	GS, SDS, Efficient 3D Content Creation	PKU / NTU	DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation	ICLR 2024 Oral	github
2023-09-04	Multi-View Consistent Images, Single Image	HKU	SyncDreamer: Generating Multiview-consistent Images from a Single-view Image	ICLR 2024 Spotlight	github
2023-08-31	Multi-View Diffusion, 3D Generation	UCSD / ByteDance	MVDream: Multi-view Diffusion for 3D Generation	ICLR 2024	project
2023-08-22	IT3D, Explicit View, Text-to-3D	NTU	IT3D: Improved Text-to-3D with Explicit View Synthesis	NeurIPS 2023	paper
2023-06-30	Magic123, One Image to 3D, 2D+3D Priors	KAUST / Snap	Magic123: One Image to High-Quality 3D Object Using Both 2D and 3D Diffusion Priors	CVPR 2024	project
2023-06-29	Single Image, Optimization-Free, Mesh	Shanghai AI Lab	One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization	NeurIPS 2023	github
2023-06-21	DreamTime, Improved SDS, Optimization	IDEA / HKU	DreamTime: An Improved Optimization for Diffusion-Guided 3D	ICLR 2024	paper
2023-06-06	ATT3D, Amortized, Text-to-3D	NVIDIA	ATT3D: Amortized Text-to-3D Object Synthesis	ICCV 2023	paper
2023-05-30	HiFA, High-Fidelity, Text-to-3D, Advanced Guidance	UIUC	HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance	ICLR 2024	paper
2023-05-25	Text-to-3D, Variational SDS, High-Fidelity, Spotlight	Tsinghua	ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation	NeurIPS 2023 Spotlight	project
2023-03-24	Make-It-3D, Single Image, Diffusion Prior	SJTU / Microsoft	Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior	ICCV 2023	project
2023-03-24	Text-to-3D, Geometry+Appearance Disentangle	SCUT	Fantasia3D: Disentangling Geometry and Appearance for Text-to-3D	ICCV 2023	project
2023-03-20	Zero-1-to-3, Zero-Shot, Single Image to 3D	Columbia / TRI	Zero-1-to-3: Zero-shot One Image to 3D Object	ICCV 2023	github
2023-02-21	RealFusion, Single Image, 360°, 3D	Oxford VGG	RealFusion: 360° Reconstruction of Any Object from a Single Image	CVPR 2023	project
2023-01-26	3DShape2VecSet, Neural Fields, Diffusion, Mesh	KAUST / TUM	3DShape2VecSet: A 3D Shape Representation for Neural Fields and Diffusion	SIGGRAPH 2023 (ACM TOG)	github
2022-12-02	DiffRF, Rendering-Guided, Radiance Field Diffusion, Highlight	TUM / Meta	DiffRF: Rendering-Guided 3D Radiance Field Diffusion	CVPR 2023 Highlight	paper
2022-12-01	Text-to-3D, Score Jacobian Chaining, 2D Diffusion	TTI-Chicago	Score Jacobian Chaining: Lifting Pretrained 2D Diffusion for 3D	CVPR 2023	paper
2022-11-18	Text-to-3D, High-Res, Coarse-to-Fine, Highlight	NVIDIA	Magic3D: High-Resolution Text-to-3D Content Creation	CVPR 2023 Highlight	paper
2022-10-12	LION, Latent Point Diffusion, Shape	NVIDIA	LION: Latent Point Diffusion Models for 3D Shape Generation	NeurIPS 2023	github
2022-09-29	Text-to-3D, Score Distillation, SDS, 2D Diffusion, Outstanding Paper	Google Research	DreamFusion: Text-to-3D using 2D Diffusion	ICLR 2023 Outstanding Paper	project
2022-09-22	GET3D, Generative, Textured Shapes, Images Only	NVIDIA	GET3D: A Generative Model of High Quality 3D Textured Shapes	NeurIPS 2022	github
2022-03-17	AutoSDF, Shape Prior, 3D Completion	CMU	AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation	CVPR 2022	paper
2020-02-23	PolyGen, Autoregressive, Mesh, DeepMind	DeepMind	PolyGen: An Autoregressive Generative Model of 3D Meshes	ICML 2020	paper

Multi-Image / Multi-View Object Mesh

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-06-23	Multi-View + LiDAR, Vehicle Assets, TRELLIS	Shanghai Jiao Tong University	MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving	arXiv	github
2026-03-12	Multi-View, SAM3D, Layout-Aware, Physical Plausibility	Peking University	MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation	arXiv	github
2026-01-16	Casual Capture, Posed Multi-View, Metric Shape	Meta AI	ShapeR: Robust Conditional 3D Shape Generation from Casual Captures	arXiv	paper
2025-11-12	Multi-Image Fusion, Region Control, TRELLIS	Zhejiang University	Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion	SIGGRAPH Asia 2025	project / github
2025-03-18	Multi-View Image-to-Shape, Hunyuan3D-DiT	Tencent	Hunyuan3D 2.0 MV	Model	github / model
2024-02-06	Scalable View Synthesis, Single/Multi-Image 3D	KAUST	EscherNet: A Generative Model for Scalable View Synthesis	CVPR 2024	project
2019-08-05	Multi-View Images, Mesh Deformation, Shape Refinement	National Tsing Hua University	Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation	ICCV 2019	github

4.1.2 Texture & Material Generation (PBR)

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-25	Relightable 3D Assets, PBR Maps, Gaussian Representation	Apple	Luce: Relightable Gaussians for 3D Asset Generation	arXiv	paper
2026-08-24	Material Decomposition, Physical Properties, Watertight Sub-Meshes, Sim-Ready	University of Bristol	Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition	arXiv	paper
2026-07-01	Complex Textures, Video Generative Prior, 3D Assets	Authors	Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models	arXiv	paper
2024-11-10	VLM-Guided, PBR Texture	3D AIGC	TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting	CVPR 2025	project
2024-01-17	TextureDreamer, Geometry-Aware, Diffusion	UCSD / Meta	TextureDreamer: Image-Guided Texture Synthesis	CVPR 2024	paper
2023-12-21	Texture Generation, Mesh, Multi-View Consistency	Tencent	Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models	CVPR 2024	project
2023-11-28	SceneTex, Indoor, Texture, Diffusion, Highlight	TUM / Snap	SceneTex: High-Quality Texture Synthesis for Indoor Scenes	CVPR 2024 Highlight	paper
2023-11-21	SyncMVD, Multi-View, Text-to-Texture	CUHK	SyncMVD: Text-Guided Texturing by Synchronized Multi-View Diffusion	CVPR 2024	paper
2023-08-22	PBR Material, SVBRDF, Text-to-Material	Adobe	MatFuse: Controllable Material Generation with Diffusion Models	SIGGRAPH Asia 2024	project
2023-03-20	Texture, Material, Text-to-Texture	KAIST	Text2Tex: Text-driven Texture Synthesis via Diffusion Models	ICCV 2023	project
2023-02-03	TEXTure, Text-Guided, 3D Texture, Diffusion	Tel Aviv University	TEXTure: Text-Guided Texturing of 3D Shapes	SIGGRAPH 2023	project
2022-07-06	nvdiffrec, 3D Mesh, Material, Lighting, Oral	NVIDIA	nvdiffrec: Extracting Triangular 3D Models, Materials, and Lighting	CVPR 2022 Oral	github

4.2 Part-Level & Articulated Generation

4.2.1 Kinematic Structure Generation

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-08	Single Image, Physical CoT, URDF, Simulation-Ready	Aerospace Information Research Institute, CAS	PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets	arXiv	paper
2026-07-15	Articulation + Physics, 40K Assets, Simulation-Ready	Zhejiang University	UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets	arXiv	github
2026-05-20	Rigid/Deformable/Articulated, Physical Attributes, Sim-Ready	Nanyang Technological University	PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects	arXiv	project / dataset
2026-05-14	Agentic Generation, Articraft-10K, URDF Assets	Authors	Articraft: An Agentic System for Scalable Articulated 3D Asset Generation	arXiv	project / github
2026-05-06	Physics-Grounded, Kinematic, Simulation-Ready Assets	HKU	PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World	ICML 2026	project / github
2026-03-14	URDF, Autoregressive, Simulation-Ready Assets	Authors	URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets	arXiv	paper
2026-03-01	Articulated Assets, 3D LLM, Kinematic Structure	Tsinghua	ArtLLM: Generating Articulated Assets via 3D LLM	CVPR 2026	paper
2025-12-12	Articulation, Kinematic Tree, Feed-Forward, URDF-Ready	University of Oxford	Particulate: Feed-Forward 3D Object Articulation	arXiv	project
2025-11-26	Single Image, Open-Set Articulation, Unified Latent	ShanghaiTech	UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation	arXiv	paper
2025-11-17	Sim-Ready Assets, Physical Properties, Single Image	NTU	PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image	CVPR 2026	paper
2025-11-02	URDF, 3D MLLM, Articulated Objects	Tsinghua	URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model	NeurIPS 2025	paper
2025-08-20	Articulated Geometry, Motion Modeling, Gaussian Representation	Tsinghua University	GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects	3DV 2026	paper
2025-07-16	Physical Properties, Scale, Material, Affordance	Nanyang Technological University	PhysX-3D: Physical-Grounded 3D Asset Generation	NeurIPS 2025 Spotlight	project / github
2025-06-10	Interactable Digital Twin, Articulated Object, RGB-D Video	Shanghai Jiao Tong University	iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos	3DV 2026	paper
2025-04-17	Simulation-Ready, Physical Materials, Dynamics	University of Massachusetts Amherst	SOPHY: Generating Simulation-Ready Objects with Physical Materials	WACV 2026	project / github
2025-03-11	Part-Level Digital Twin, Joint Estimation, Self-Supervised 3DGS	USTC	ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting	CVPR 2025	paper
2025-02-26	Articulated Objects, 3DGS, Joint Estimation	Tsinghua	ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting	ICLR 2025	project
2025-02-17	Articulation-Ready, Skeleton, Skinning, Benchmark	Nanyang Technological University	MagicArticulate: Make Your 3D Models Articulation-Ready	CVPR 2025	project / github
2024-09-26	Open-Vocabulary, URDF, Articulation	Stanford	Articulate Anything: Open-vocabulary 3D Articulated Object Generation	ICLR 2025	project

4.2.2 Part-Aware Assembly & Editing

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-08-20	Compositional 3D, Part Semantics, Spatial Control, Reassemblable Assets	Roblox	MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Control	arXiv	project
2026-08-14	Up to 300 Parts, Token-Efficient VQ, Autoregressive 3D, Structured Assets	The University of Hong Kong	MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling	arXiv	project
2026-08-13	Part-Aware Generation, Recursive Decomposition, Editable Assets	Shanghai Jiao Tong University	SCULPT: Subtractive Composition for 3D Part Generation	arXiv	project
2026-07-18	Category-Agnostic, Neural Shape Editing, Coupled Representation	Authors	CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation	arXiv	paper
2026-06-23	Garment Patterns, Simulation-Ready, Editing	University of Hong Kong	PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments	arXiv	github
2026-05-27	Part-Controllable, Open-Vocabulary, Game-Ready	Roblox	CubePart: An Open-Vocabulary Part-Controllable 3D Generator	SIGGRAPH 2026	project / model
2025-09-10	Part Decomposition, Editable, Production-Ready Assets	Tencent	X-Part: High-Fidelity and Structure-Coherent Shape Decomposition	Tech Report	project
2025-08-14	Rigging, Animation, Skeleton, Skinning	Nanyang Technological University	Puppeteer: Rig and Animate Your 3D Models	NeurIPS 2025 Spotlight	project / github
2025-06-05	Part-Level Mesh, Compositional DiT, Single Image	University of Waterloo	PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers	arXiv	project
2024-12-16	Articulated Mesh, Part-by-Part, Hierarchical Transformer	Cornell	MeshArt: Generating Articulated Meshes with Structure-Guided Transformers	arXiv	paper
2023-12-13	Shape Program, Structure, Editable Assets	MIT	Shape2Program: Learning to Infer Shape Programs from 3D Shapes	arXiv	project
2023-06-29	Part-Aware, Shape Assembly, 3D Generation	Shanghai AI Lab	Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation	NeurIPS 2023	github

4.3 Scene-Level Generation

4.3.1 Layout & Procedural Generation

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-09-10	Single Image, Executable Scene Programs, Recursive Construction, Editable 3D	Georgia Institute of Technology	Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs	arXiv	paper
2026-09-05	Agentic 3D Composition, Functional Objects, Executable Robot Scenes	Peking University / Galbot	GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning	arXiv	paper
2026-09-04	Image-to-Scene, Agentic Layout Evolution, Simulation-Ready Diversity	The University of Hong Kong	SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution	arXiv	project / github
2026-08-31	Text-to-Scene, Grow-and-Repair, Functional Groups, SceneReverse-17K	Southeast University	ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation	arXiv	project
2026-08-27	Single Image, Generative 3D Proxy, RGB-D World Expansion, Explorable Scene	Hong Kong University of Science and Technology	SpatialCrafter: Single Image World Modeling with Generative 3D Proxies	arXiv	project
2026-08-25	Monocular Image, Interactive Scene Programming, Articulation+Physics, Embodied Simulation	Shanghai Jiao Tong University	NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation	arXiv	project
2026-08-19	Usage-Driven Code Scenes, Multi-Part Interaction, Executable Simulation	Shanghai Jiao Tong University	Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction	arXiv	paper
2026-07-29	Panoramic Video, 3DGS, Simulation-ready World	AgiBot	Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation	arXiv	github
2026-07-15	Indoor Layout, Progressive VLM Reasoning, Interactive Editing	City University of Hong Kong	ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning	arXiv	paper
2026-07-08	Simulation-Ready Assets, Affordances, Cross-Simulator Worlds	Horizon Robotics	EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI	arXiv	project / github
2026-07-07	Real-to-Sim, One-Shot Scene Generation, Robot Evaluation	Shanghai AI Lab	RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation	arXiv	project
2026-07-04	Egocentric Scene Generation, Geometric 3DGS, Consistency	South China Univ. of Technology	CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation	arXiv	paper
2026-06-23	Triangle Splatting, Single-Image Scene, Game-Ready	Google Research	FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation	arXiv	project
2026-06-23	Text-to-Scene, Video Priors, 3DGS Orbit	University of Bern	OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis	arXiv	paper
2026-06-23	Compositional 3D, Physical Interaction, Multi-View Consistency	China University of Petroleum (East China)	Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation	arXiv	paper
2026-06-23	Satellite-to-City, Textured Mesh, Urban Simulation	HKUST(GZ)	Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image	arXiv	paper
2026-06-08	Satellite-to-3D, 3DGS, UAV Simulation	Amap-cvlab / Alibaba	ABot-Earth 0.5: Generative 3D Earth Model	arXiv	project
2026-06-04	Whole-Home Scenes, Floorplans, Interactive	Authors	HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes	arXiv	paper
2026-05-28	Physical Stability, Single Image, Scene Tree, Simulation	Carnegie Mellon University	REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image	arXiv	project
2026-05-01	Segment Map, Text-to-World, Controllable 3D Worlds	Seoul National University	Map2World: Segment Map Conditioned Text to 3D World Generation	arXiv	paper
2026-04-14	Explorable 3D Worlds, Long Trajectory, 3DGS	NVIDIA	Lyra 2.0: Explorable Generative 3D Worlds	arXiv	project
2026-04-06	Single-Image Scene, In-Place Completion, ARSG-110K	Nankai University	3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image	CVPR 2026	project / github / dataset
2026-03-31	Town-Scale, Single Image, Latent Extension	Seoul National University	Extend3D: Town-Scale 3D Generation	CVPR 2026	project
2026-03-31	Unbounded World, Flow Matching, Layouts	Princeton University	WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation	arXiv	project
2026-03-27	Autoregressive 3DGS, Token Generation, Completion/Outpainting	Technical University of Munich	GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation	arXiv	project
2026-03-12	Multi-Floor, Language-to-3D, Long-Horizon Tasks	Tsinghua	MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks	CVPR 2026	paper
2026-03-06	Compositional Scene, Panoramic Image, Feed-Forward	NTU	Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image	CVPR 2026	paper
2026-02-10	Agentic Scene Generation, Sim-Ready, SAGE-10k	NVIDIA	SAGE: Scalable Agentic 3D Scene Generation for Embodied AI	CVPR 2026	project / github
2026-01-09	Language-Guided, Infinite Worlds, Articulated Furniture	National Taiwan Univ	SceneFoundry: Generating Interactive Infinite 3D Worlds	arXiv	project
2025-12-01	Tabletop, Instance-Level, Interactive Scene, Text/Image	D-Robotics	TabletopGen: Instance-Level Interactive 3D Tabletop Scene Generation from Text or Single Image	arXiv	project / paper
2025-11-18	Single-Image Scene, Gaussian World, Scene Generation	Tsinghua University	GEN3D: Generating Domain-Free 3D Scenes from a Single Image	arXiv	paper
2025-09-18	Layout-Guided, Indoor Scenes, Decoupled Geometry/Appearance	Hong Kong University of Science and Technology	SPATIALGEN: Layout-guided 3D Indoor Scene Generation	3DV 2026	paper
2025-08-21	Single Image, Multi-Asset Scene, Feed-Forward	Shanghai Jiao Tong University	SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass	3DV 2026	project / github
2025-08-11	Panoramic, Explorable World, Matrix-Pano	Kunlun Wanwei	Matrix-3D: Omnidirectional Explorable 3D World Generation	arXiv	project / github
2025-07-29	Panoramic, Text/Image-to-World, Mesh Export	Tencent Hunyuan	HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels	arXiv	github
2025-07-09	VLA Scene Authoring, Simulation-Ready Worlds, Synthetic Data	NVIDIA / Stanford University	3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds	3DV 2026	project / github
2025-06-25	Explorable Scene, Novel-View Restoration, Consistency	Beijing Academy of AI	WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration	arXiv	paper
2025-03-13	Scene Layout, Optimization, Generation	Tsinghua	HOG-Layout: Layout-Enhanced Scene Generation via Hierarchical Optimization	arXiv	project
2025-02-20	Octree, 3D Diffusion, Scene Generation	Zhejiang University	Octree Diffusion: Hierarchical Scene Generation via Octree Structures	arXiv	project
2025-01-15	Gaussian, GPT, Scene Generation	Shanghai AI Lab	GaussianGPT: Language-Driven Scene Generation with Gaussian Representation	arXiv	paper
2024-12-19	Scene Generation, Growing, Incremental	Tsinghua	WorldGrow: Incremental 3D Scene Generation	CVPR 2025	project
2024-11-05	Splatting, Fluents, Scene Understanding	University of Cambridge	FluSplat: Fluent Scene Generation via Gaussian Splatting	CVPR 2025	project
2024-11-04	GenXD, Any 3D and 4D, Scene Generation	NUS	GenXD: Generating Any 3D and 4D Scenes	ICLR 2025	paper
2024-06-17	Procedural Scenes, Synthetic Data, Embodied AI	Princeton	Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation	NeurIPS 2024	project / github
2024-06-13	Interactive 3D Scene, FLAGS, Single Image	Stanford University	WonderWorld: Interactive 3D Scene Generation from a Single Image	CVPR 2025	project
2024-05-02	EchoScene, Scene Graph, Diffusion, Indoor	TUM / JHU	EchoScene: Indoor Scene Generation via Information Echo	ECCV 2024	paper
2024-02-12	SceneScape, Text-Driven, Consistent, Scene	Weizmann	SceneScape: Text-Driven Consistent Scene Generation	NeurIPS 2024	paper
2024-01-30	BlockFusion, Expandable, Tri-plane, SIGGRAPH	Tencent / UTokyo	BlockFusion: Expandable 3D Scene Generation	SIGGRAPH 2024 (ACM TOG)	paper
2023-12-01	ControlRoom3D, Semantic Proxy, Room Generation	TUM / Meta	ControlRoom3D: Room Generation using Semantic Proxy Rooms	CVPR 2024	paper
2023-10-05	Ctrl-Room, Text-to-3D, Layout Constraints	Simon Fraser	Ctrl-Room: Controllable Text-to-3D Room Meshes Generation	ECCV 2024	paper
2023-10-04	MagicDrive, Street View, 3D Geometry Control	CUHK / HKUST	MagicDrive: Street View Generation with Diverse 3D Geometry Control	ICLR 2024	project
2023-06-15	Procedural World, Synthetic Data, Simulation	Princeton	Infinite Photorealistic Worlds using Procedural Generation	CVPR 2023	project
2023-03-24	DiffuScene, Diffusion, Indoor Scene Synthesis	TUM	DiffuScene: Denoising Diffusion for Generative Indoor Scene Synthesis	CVPR 2024	paper
2023-03-21	Text-to-3D Room, Indoor Scenes, Mesh	LMU Munich	Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models	ICCV 2023	project
2023-02-02	Unbounded 3D Scene, Generative Model, Driving	NVIDIA	SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections	CVPR 2023	project

4.3.2 Semantic Scene Generation & Spatial Intelligence

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-18	Multi-View Generation, Scene Assets, Training-Free	The University of Queensland	Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning	arXiv	github
2025-01-03	Rover, Semantic, 3D Scene	Carnegie Mellon University	SEM-ROVER: Semantic Scene Exploration with Hierarchical Spatial Reasoning	ICLR 2025	project
2024-09-30	Spatial, Generation, Language	Tsinghua	SpatialGen: Language-Driven Spatial Scene Generation	NeurIPS 2024	project

4.3.3 4D / Dynamic Scene Generation

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-11	Layout-Conditioned, 3DGS, Mixed Reality	Authors	SyncSpace: Layout-Conditioned 3D Gaussian Splatting for Space Reskinning in Mixed Reality	arXiv	paper
2025-04-17	Image-Pair-to-4D, Diffusion, Explicit 3D Motion	Technical University of Munich	TwoSquared: 4D Generation from 2D Image Pairs	3DV 2026 Oral	paper
2024-12-05	4Real-Video, Photo-Realistic, Video Diffusion, CVPR	Snap / KAUST	4Real-Video: Generalizable Photo-Realistic 4D Video Diffusion	CVPR 2025	paper
2024-07-16	Animate3D, Multi-View, Video Diffusion, NeurIPS	CASIA / Alibaba	Animate3D: Animating Any 3D Model with Multi-view Video Diffusion	NeurIPS 2024	paper
2024-05-31	4Diffusion, Multi-View Video, 4D, NeurIPS	CASIA / Shanghai AI Lab	4Diffusion: Multi-view Video Diffusion Model for 4D Generation	NeurIPS 2024	paper
2024-05-26	Diffusion4D, Video Diffusion, 4D, NeurIPS	Toronto / BJTU	Diffusion4D: Fast Spatial-temporal Consistent 4D Generation	NeurIPS 2024	paper
2024-05-03	DreamScene4D, Multi-Object, Dynamic, NeurIPS	CMU	DreamScene4D: Dynamic Multi-Object Scene Generation	NeurIPS 2024	paper
2024-03-22	STAG4D, Spatial-Temporal, 4D Gaussians, ECCV	Nanjing / CASIA	STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians	ECCV 2024	paper
2023-11-29	4D-fy, Text-to-4D, Score Distillation, CVPR	KAUST / Snap	4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling	CVPR 2024	project
2023-11-24	Animate124, Image-to-4D, Animation, ICLR	NUS / Huawei	Animate124: Animating One Image to 4D Dynamic Scene	ICLR 2024	paper
2023-11-17	Consistent4D, 360° Dynamic, Monocular Video, ICLR	CASIA / Nanjing	Consistent4D: Consistent 360° Dynamic Object Generation	ICLR 2024	project

4.4 3D Editing

3D editing covers methods that modify existing 3D assets, Gaussian / NeRF fields, meshes, voxel or latent states, and dynamic scenes. Entries are grouped by editable state: object-level, scene-level, and dynamic / 4D.

4.4.1 Object-Level Editing

Date	Keywords	Institute (first)	Paper / Resource	Publication	Others
2026-07-27	NeRF Editing, Object Removal, Robot Manipulation	Authors	NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation	arXiv	paper
2026-06-05	Mesh Editing, Image-Guided, Local Morphing	Leiden University	3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing	IJCNN 2026	github
2026-05-26	PartFlow, Semantic-Part Transformation, Mask-Free	Nanyang Technological University	Feedforward 3D Editing Learns from Semantic-Part Transformation	arXiv	project / github / benchmark (Steer3D)
2026-05-08	VS3D, Velocity-Space, Mask-Free	Tsinghua University	Velocity-Space 3D Asset Editing	arXiv	paper
2026-05-01	Latent Editing, Object-Level, Structured 3D Latents	Seoul National University	InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization	arXiv	project
2026-04-30	MeshReGen, VecSet Regeneration, Image-Guided Editing	KAIST	MeshReGen: A Unified 3D Geometry Regeneration Framework	arXiv	project / benchmark (VoxHammer)
2026-04-26	Primitive Proxy, Shape Editing, Fine-Grained Control	Tel Aviv University	Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions	SIGGRAPH 2026	project / github / benchmark (VoxHammer)
2026-03-30	3DGS Editing, Object-Level, Single-View	Zhejiang Gongshang University	SVGS: Single-View to 3D Object Editing via Gaussian Splatting	ACM TOMM 2026	project
2026-02-25	Voxel Editing, Object-Level, Rectified Voxel Flow	USTC	Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow	CVPR 2026	project
2026-02-05	Native 3D Editing, Image-Conditioned, Latent-to-Latent	Aigency.ai / Tel Aviv University	ShapeUP: Scalable Image-Conditioned 3D Editing	SIGGRAPH 2026	project / github
2026-02-04	Mesh Editing, Object-Level, Single-Image LRM	National Yang Ming Chiao Tung University	VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image	arXiv	github / benchmark (VoxHammer)
2025-12-15	Steer3D, Text-Steerable, Edit3D-Bench (Ma)	Caltech	Feedforward 3D Editing via Text-Steerable Image-to-3D	arXiv	project / github / benchmark (Steer3D)
2025-11-27	Latent Anchor, Object-Level, Mask-Free	Zhejiang University	AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows	CVPR 2026 Oral	project / github / benchmark
2025-11-21	Native Editing, Object-Level, Full Attention	Fudan University / StepFun	Native 3D Editing with Full Attention	arXiv	paper
2025-10-16	FlowEdit, Object-Level, Mask-Free	Tsinghua University	NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks	ICLR 2026	project / github / dataset
2025-10-03	3DEditFormer, Paired Dataset, Mask-Free	East China Univ of Science & Technology	Towards Scalable and Consistent 3D Editing	arXiv	project / github
2025-08-29	3D-LATTE, Text Instructions, 3D Diffusion Latent	University of Tübingen	3D-LATTE: Latent Space 3D Editing from Textual Instructions	CVPR 2026 Oral	project / CVF
2025-08-26	VoxHammer, Edit3D-Bench (Li), Training-Free	Renmin University / Beihang University	VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space	3DV 2026 Oral	project / github / benchmark (VoxHammer)
2025-07-15	3DGS Editing, Part-Level, Regularized SDS	Seoul National University	Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling	ICCV 2025	CVF
2025-06-25	Image Prompt, Multi-View Propagation, Mask-Free	Tel Aviv University	EditP23: 3D Editing via Propagation of Image Prompts to Multi-View	ACM TOG 2025	project / github
2025-05-11	CMD, Local Editing, Progressive Generation	HKUST	CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation	SIGGRAPH 2025	project
2024-12-11	Mesh Editing, Object-Level, Masked LR

Truncated — view the full README on GitHub.

3d-generation

3d-reconstruction

3d-vision

awesome-list

computer-vision

embodied-ai

gaussian-splatting

nerf

robotics

world-models

Contributors

github-actions[bot]

98 commits

chang-xinhai

53 commits

Similar repos

ziplab/Awesome-Feed-Forward-3D

An curated list for feed-forward 3D scene modeling, including research directions, datasets, and…

292

yyeboah/Awesome-Text-to-3D

A growing curation of Text-to-3D, Diffusion-to-3D works.

603

dragonlong/Trending-in-3D-Vision

An on-going paper list on new trends in 3D vision with deep learning

333

DoranLyong/oh-my-world-intelligence

From 3D/4D Scene Understanding to Semantic-metric World Models

2hiTee/awesome-3D-Generation

This is a collective repository for all 3D and 4D Object Generation papers

yukangcao/Awesome-4D-Spatial-Intelligence

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv…

526

justimyhxu/awesome-3D-generation

A curated list of awesome 3d generation papers

1,198

worldbench/awesome-3d-4d-world-models

[TPAMI 2026] 3D and 4D World Modeling: A Survey

989

Languages

Python

100.0%

chang-xinhai/Awesome-Embodied-3DV

A curated map of 3D/4D perception, reconstruction, generation, simulation-ready assets, and world models for embodied AI.

Python

151 commits

updated Sep 23, 2026

See the code

README

Awesome-Embodied-3DV

A curated map of 3D/4D perception, reconstruction, generation, simulation-ready assets, and world models for embodied AI.

About

Awesome-Embodied-3DV is a curated list for the research space where 3D vision, 3D/4D reconstruction, 3D generation, simulation-ready assets, and embodied world models meet.

This repository focuses on:

Data Perception: depth, normals, active imaging, panoramic/fisheye, dense mapping, and 3D semantic understanding (detection, segmentation, grounding) that feed downstream systems
3D/4D Representation: 3DGS, 4DGS, NeRF/SDF, mesh, voxel, point, and hybrid structures
3D Reconstruction: offline, feed-forward, streaming, online, semantic, instance-level, and dynamic reconstruction
3D Generation: object-level, part-level, articulated, scene-level, editable, and simulation-ready asset generation
Embodiment & World Models: reconstruction-based world models, dynamic scene graphs, physical interaction & affordance, human-centric 3D, robotics integration, and agent-facing 3D grounding
Datasets, Benchmarks & Infrastructure: datasets, metrics, simulators, toolchains, and surveys for fast research orientation

Must Read

Start here if you want the shortest path through the field.

Goal	Start with
Estimate temporally consistent video depth	Video Depth Anything, FlashDepth, ICDepth, ViGeo, DVD, RollingDepth
Deploy zero-shot monocular depth at the edge	ZipDepth, DepthART
Recover metric-scale geometry from RGB	MetricAnything, Metric DAv2, Depth Pro, UniDepthV2
Understand feed-forward 3D reconstruction	Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey, DUSt3R, MASt3R, VGGT
Track online / streaming 3D reconstruction	Dynamic 3D Gaussians, CUT3R, Spann3R, SLAM3R, StreamSplat, UniSim-SLAM
Study dynamic 4D feed-forward geometry	PAGE-4D, 4D-VGGT, DynamicVGGT
Learn representation foundations	3D Gaussian Splatting, NeRF, Instant-NGP, TensoRF
Generate object and simulation-ready assets	TRELLIS, Hunyuan3D 2.0, TripoSR, PartCrafter
Generate scenes and worlds	Infinigen, SceneDreamer, Text2Room, WonderWorld, EmbodiedGen V2
Build articulated objects	ArtGS, Articulate Anything, URDF-Anything, URDF-Anything+, PartNet-Mobility
Build an open-vocabulary 3D robot memory	CLIP-Fields, ConceptFusion, Open-Fusion, ConceptGraphs
Build persistent, action-conditioned 3D world models	Learning 3D Persistent Embodied World Models, GEN3C, NeoVerse, Genie 4D, BWM
Pick datasets and benchmarks	ScanNet, Tanks and Temples, DTU, Objaverse, GSO, HM3D, TransBiolab

News

[2026-08-04] Added a six-topic, automatically refreshed arXiv Daily candidate archive, with manual verification required before promotion to this curated list.
[2026-06-15] Added a dedicated 3D Editing taxonomy under 3D Generation, covering object-level, scene-level, and dynamic / 4D editing methods.
[2026-04-30] Initialized Awesome-Embodied-3DV with a six-part taxonomy for data perception, representations, reconstruction, generation, embodied world models, and infrastructure.

Awesome-Embodied-3DV