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 839 篇，第 1 / 17 页

1. NeurIPS 2026$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
2. NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
3. NeurIPS 20263D Consistency Tokens
4. NeurIPS 20263D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
5. NeurIPS 20263D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identification
6. NeurIPS 20263R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
7. NeurIPS 2026A Dual-Domain Vision Transformer with Spectral Positional Bias
8. NeurIPS 2026ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
9. NeurIPS 2026Adapting Vision Transformers to Organoid Imaging
10. NeurIPS 2026AEON: Unifying Video and 3D World Models
11. NeurIPS 2026Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks
12. NeurIPS 2026Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
13. NeurIPS 2026Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
14. NeurIPS 2026Attention Transfer Is Not Universally Effective for Vision Transformers
15. NeurIPS 2026Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
16. NeurIPS 2026Augmented Equivariant Mesh Networks for Anatomical Segmentation
17. NeurIPS 2026Autoregressive Appearance Prediction for 3D Gaussian Avatars
18. NeurIPS 2026BA-T: An Iterative Transformer for Two-View Bundle Adjustment
19. NeurIPS 2026BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
20. NeurIPS 2026BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
21. NeurIPS 2026Blur Issue Matters for Thermal Novel View Synthesis: A Floating Gaussian Suppression Approach
22. NeurIPS 2026Bounding Global and Local Compression Error of Signal Parameterizations
23. NeurIPS 2026BridgeMVS: Bridging Multi-View Stereo and Monodepth via Bidirectional Dynamic Fusion
24. NeurIPS 2026Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling
25. NeurIPS 2026C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance
26. NeurIPS 2026CC-GS: Low-Memory 3D Gaussian Splatting Training via CPU-GPU Block-Wise Context Compositing
27. NeurIPS 2026CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy
28. NeurIPS 2026Certifiably Optimal Robust Angular Synchronization
29. NeurIPS 2026Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers
30. NeurIPS 2026ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
31. NeurIPS 2026Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks
32. NeurIPS 2026Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
33. NeurIPS 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
34. NeurIPS 2026Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
35. NeurIPS 2026CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
36. NeurIPS 2026COHE: Auditing Non-Transitivity in Sample Difficulty Proxies for Vision Models
37. NeurIPS 2026Complexity Aware Continuous Level of Details for Gaussian Splatting
38. NeurIPS 2026Complexity-guided Regularization for Generalizable Human Gaussian Splatting
39. NeurIPS 2026Concord-SLAM: Cross-Render Concordance for Boundary-Native Semantic Gaussian SLAM
40. NeurIPS 2026Contextualized Evaluation of Vision Language Models through Dynamic Interviews
41. NeurIPS 2026ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling
42. NeurIPS 2026Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
43. NeurIPS 2026Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration
44. NeurIPS 2026Deformable 2D Gaussian Splatting
45. NeurIPS 2026Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty Aware Differentiable Optimization
46. NeurIPS 2026Diffeomoprhism-Informed 3D Gaussian Splattings via Screen-Space Optimal Transport (OT)
47. NeurIPS 2026Diffusion Masked Pretraining for Dynamic Point Cloud
48. NeurIPS 2026DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation
49. NeurIPS 2026Direct Conditional Parameterization for N-Dimensional Splatting
50. NeurIPS 2026Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision

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。