三维视觉论文趋势 2023–2026

主要结论

• 三维视觉论文从 2023 年的 563 篇增长到 2026 年的 1,010 篇，三年间扩大到约 1.8 倍。
• CVPR 是发三维视觉论文最多的会议，2023–2026 年共 1,641 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是高斯过程：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 158 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的视频理解是 2.6 倍，三维视觉是 1.8 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
• ICML 20263D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
• ICLR 2026$\pi^3$: Permutation-Equivariant Visual Geometry Learning
• CVPR 20262D-LFM Lifting Foundation Model without 3D Supervision
• NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
• ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
• ICLR 20253D StreetUnveiler with Semantic-aware 2DGS - a simple baseline
• CVPR 20253D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
• NeurIPS 20243D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
• ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
• ICLR 20243D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
• CVPR 2024DaReNeRF: Direction-aware Representation for Dynamic Scenes
• NeurIPS 2023[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
• ICML 2023Efficient Graph Field Integrators Meet Point Clouds
• ICLR 2023$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
• CVPR 20233D Cinemagraphy From a Single Image
• NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
• ICML 20263DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
• ICLR 20263DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
• CVPR 20263D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors

全部三维视觉论文

共 902 篇，第 1 / 19 页

1. CVPR 20253D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
2. CVPR 20253D Gaussian Inpainting with Depth-Guided Cross-View Consistency
3. CVPR 20253D Student Splatting and Scooping
4. CVPR 20253D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation
5. CVPR 20253D-GSW: 3D Gaussian Splatting for Robust Watermarking
6. CVPR 20253D-HGS: 3D Half-Gaussian Splatting
7. CVPR 20253DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
8. CVPR 20254D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models
9. CVPR 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
10. CVPR 2025A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
11. CVPR 2025A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions
12. CVPR 2025A Unified Approach to Interpreting Self-supervised Pre-training Methods for 3D Point Clouds via Interactions
13. CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
14. CVPR 2025Active Event-based Stereo Vision
15. CVPR 2025ActiveGAMER: Active GAussian Mapping through Efficient Rendering
16. CVPR 2025Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception
17. CVPR 2025Advancing Adversarial Robustness in GNeRFs: The IL2-NeRF Attack
18. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
19. CVPR 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
20. CVPR 2025AffordDP: Generalizable Diffusion Policy with Transferable Affordance
21. CVPR 2025An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
22. CVPR 2025AniGrad: Anisotropic Gradient-Adaptive Sampling for 3D Reconstruction From Monocular Video
23. CVPR 2025AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
24. CVPR 2025AnyMap: Learning a General Camera Model for Structure-from-Motion with Unknown Distortion in Dynamic Scenes
25. CVPR 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
26. CVPR 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
27. CVPR 2025ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points
28. CVPR 2025Argus: A Compact and Versatile Foundation Model for Vision
29. CVPR 2025ARM: Appearance Reconstruction Model for Relightable 3D Generation
30. CVPR 2025ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting
31. CVPR 2025Associative Transformer
32. CVPR 2025ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
33. CVPR 2025AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting
34. CVPR 2025AutoURDF: Unsupervised Robot Modeling from Point Cloud Frames Using Cluster Registration
35. CVPR 2025BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting
36. CVPR 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
37. CVPR 2025BG-Triangle: Bezier Gaussian Triangle for 3D Vectorization and Rendering
38. CVPR 2025BHViT: Binarized Hybrid Vision Transformer
39. CVPR 2025BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
40. CVPR 2025BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
41. CVPR 2025BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing
42. CVPR 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior
43. CVPR 2025Building Vision Models upon Heat Conduction
44. CVPR 2025BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer
45. CVPR 2025CamPoint: Boosting Point Cloud Segmentation with Virtual Camera
46. CVPR 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image
47. CVPR 2025CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
48. CVPR 2025Chain of Semantics Programming in 3D Gaussian Splatting Representation for 3D Vision Grounding
49. CVPR 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework
50. CVPR 2025CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images

常见问题

2023–2026 年四大会议一共有多少篇三维视觉论文？

共 3,226 篇，按年份分别是 2023 年 563 篇、2024 年 751 篇、2025 年 902 篇、2026 年 1,010 篇。

NeurIPS 2026 有多少篇三维视觉论文？

NeurIPS 2026 有 211 篇三维视觉论文，上一届是 254 篇。

ICLR 2026 有多少篇三维视觉论文？

ICLR 2026 有 197 篇三维视觉论文，上一届是 162 篇。

ICML 2026 有多少篇三维视觉论文？

ICML 2026 有 117 篇三维视觉论文，上一届是 52 篇。

CVPR 2026 有多少篇三维视觉论文？

CVPR 2026 有 485 篇三维视觉论文，上一届是 434 篇。

哪个会议的三维视觉论文最多？

CVPR，2023–2026 年共 1,641 篇。