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 52 篇，第 1 / 2 页

1. ICML 20253D Question Answering via only 2D Vision-Language Models
2. ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
3. ICML 2025An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
4. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
5. ICML 2025Compositional Generalization via Forced Rendering of Disentangled Latents
6. ICML 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
7. ICML 2025CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
8. ICML 2025CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
9. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
10. ICML 2025Efficient LiDAR Reflectance Compression via Scanning Serialization
11. ICML 2025Enhancing Visual Localization with Cross-Domain Image Generation
12. ICML 2025ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
13. ICML 2025Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
14. ICML 2025ExtPose: Robust and Coherent Pose Estimation by Extending ViTs
15. ICML 2025Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
16. ICML 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
17. ICML 2025Generative Point Cloud Registration
18. ICML 2025Geometric Algebra Planes: Convex Implicit Neural Volumes
19. ICML 2025Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
20. ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
21. ICML 2025History-Guided Video Diffusion
22. ICML 2025HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
23. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
24. ICML 2025Layer by Layer: Uncovering Hidden Representations in Language Models
25. ICML 2025Learning Vision and Language Concepts for Controllable Image Generation
26. ICML 2025MiraGe: Editable 2D Images using Gaussian Splatting
27. ICML 2025MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification
28. ICML 2025One-dimensional Path Convolution
29. ICML 2025Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
30. ICML 2025Oscillation-Reduced MXFP4 Training for Vision Transformers
31. ICML 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
32. ICML 2025PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
33. ICML 2025PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning
34. ICML 2025Point Cloud Dataset Distillation
35. ICML 2025Point-Level Topological Representation Learning on Point Clouds
36. ICML 2025Position: You Can't Manufacture a NeRF
37. ICML 2025Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
38. ICML 2025Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures
39. ICML 2025ReferSplat: Referring Segmentation in 3D Gaussian Splatting
40. ICML 2025RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
41. ICML 2025Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
42. ICML 2025Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
43. ICML 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
44. ICML 2025Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
45. ICML 2025Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes
46. ICML 2025Symmetry-Robust 3D Orientation Estimation
47. ICML 2025Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
48. ICML 2025Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
49. ICML 2025Unifying 2D and 3D Vision-Language Understanding
50. ICML 2025Unpaired Point Cloud Completion via Unbalanced Optimal Transport

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。