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 511 篇，第 1 / 11 页

1. ICLR 2026$\pi^3$: Permutation-Equivariant Visual Geometry Learning
2. ICLR 20263DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
3. ICLR 20263DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud Analysis
4. ICLR 2026A Memory-Efficient Hierarchical Algorithm for Large-scale Optimal Transport Problems
5. ICLR 2026A Resolution-Agnostic Geometric Transformer for Chromosome Modeling Using Inertial Frame
6. ICLR 2026A Step to Decouple Optimization in 3DGS
7. ICLR 2026A^2TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation
8. ICLR 2026Active Learning of 3D Gaussian Splatting with Consistent Region Partition and Robust Pose Estimation
9. ICLR 2026Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
10. ICLR 2026Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
11. ICLR 2026Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
12. ICLR 2026All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting
13. ICLR 2026ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance
14. ICLR 2026AsyncBEV: Cross-modal flow alignment in Asynchronous 3D Object Detection
15. ICLR 2026Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting
16. ICLR 2026Batch Pruning by Activation Stability
17. ICLR 2026Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous Driving
18. ICLR 2026Bridging Piano Transcription and Rendering via Disentangled Score Content and Style
19. ICLR 2026cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
20. ICLR 2026Characterizing and Optimizing the Spatial Kernel of Multi Resolution Hash Encodings
21. ICLR 2026CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction
22. ICLR 2026CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
23. ICLR 2026CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
24. ICLR 2026CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
25. ICLR 2026CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
26. ICLR 2026Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer
27. ICLR 2026ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
28. ICLR 2026CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
29. ICLR 2026Condition Matters in Full-head 3D GANs
30. ICLR 2026Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives
31. ICLR 2026CroCoDiLight: Repurposing Cross-View Completion Encoders for Relighting
32. ICLR 2026CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction
33. ICLR 2026CTRL&SHIFT: High-quality Geometry-Aware Object Manipulation in Visual Generation
34. ICLR 2026Cutting the Skip: Training Residual-Free Transformers
35. ICLR 2026CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis
36. ICLR 2026D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping
37. ICLR 2026D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
38. ICLR 2026Dens3R: A Foundation Model for 3D Geometry Prediction
39. ICLR 2026Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
40. ICLR 2026DiffPBR: Point-Based Rendering via Spatial-Aware Residual Diffusion
41. ICLR 2026DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objects
42. ICLR 2026DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
43. ICLR 2026DiMeR: Disentangled Mesh Reconstruction Model with Normal-only Geometry Training
44. ICLR 2026DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision Transformer
45. ICLR 2026Distractor-free Generalizable 3D Gaussian Splatting
46. ICLR 2026DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving
47. ICLR 2026Dynamic Novel View Synthesis in High Dynamic Range
48. ICLR 2026Dynamic Texture Modeling of 3D Clothed Gaussian Avatars from a Single Video
49. ICLR 2026EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis
50. ICLR 2026EasyCreator: Empowering 4D Creation through Video Inpainting

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。