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 254 篇，第 1 / 6 页

1. NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
2. NeurIPS 20253D Equivariant Visuomotor Policy Learning via Spherical Projection
3. NeurIPS 20253D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
4. NeurIPS 20253D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion
5. NeurIPS 20253D Visual Illusion Depth Estimation
6. NeurIPS 20253D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
7. NeurIPS 20253DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
8. NeurIPS 20253EED: Ground Everything Everywhere in 3D
9. NeurIPS 20254D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
10. NeurIPS 20254D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
11. NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
12. NeurIPS 2025Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
13. NeurIPS 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
14. NeurIPS 2025AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
15. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
16. NeurIPS 2025Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression
17. NeurIPS 2025Anti-Aliased 2D Gaussian Splatting
18. NeurIPS 2025APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
19. NeurIPS 2025Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
20. NeurIPS 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
21. NeurIPS 2025AutoPartGen: Autoregressive 3D Part Generation and Discovery
22. NeurIPS 2025BEDLAM2.0: Synthetic humans and cameras in motion
23. NeurIPS 2025Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
24. NeurIPS 2025BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation
25. NeurIPS 2025Bézier Splatting for Fast and Differentiable Vector Graphics Rendering
26. NeurIPS 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
27. NeurIPS 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
28. NeurIPS 2025Building 3D Representations and Generating Motions From a Single Image via Video-Generation
29. NeurIPS 2025CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
30. NeurIPS 2025CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
31. NeurIPS 2025Cameras as Relative Positional Encoding
32. NeurIPS 2025Can NeRFs "See" without Cameras?
33. NeurIPS 2025Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment
34. NeurIPS 2025CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
35. NeurIPS 2025ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
36. NeurIPS 2025CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering
37. NeurIPS 2025CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
38. NeurIPS 2025Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
39. NeurIPS 2025Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm
40. NeurIPS 2025Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning
41. NeurIPS 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
42. NeurIPS 2025COS3D: Collaborative Open-Vocabulary 3D Segmentation
43. NeurIPS 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
44. NeurIPS 2025D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction
45. NeurIPS 2025DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting
46. NeurIPS 2025Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting
47. NeurIPS 2025DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting
48. NeurIPS 2025DGH: Dynamic Gaussian Hair
49. NeurIPS 2025DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos
50. NeurIPS 2025Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting

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。