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 563 篇，第 1 / 12 页

1. CVPR 20233D Cinemagraphy From a Single Image
2. CVPR 20233D Registration With Maximal Cliques
3. CVPR 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
4. CVPR 20233D Shape Reconstruction of Semi-Transparent Worms
5. CVPR 20233D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud
6. CVPR 20233D-Aware Multi-Class Image-to-Image Translation With NeRFs
7. CVPR 2023A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning
8. CVPR 2023ABLE-NeRF: Attention-Based Rendering With Learnable Embeddings for Neural Radiance Field
9. CVPR 2023Accidental Light Probes
10. CVPR 2023ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion
11. CVPR 2023ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction
12. CVPR 2023Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation
13. CVPR 2023AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
14. CVPR 2023ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
15. CVPR 2023AnchorFormer: Point Cloud Completion From Discriminative Nodes
16. CVPR 2023Attention-Based Point Cloud Edge Sampling
17. CVPR 2023AutoRecon: Automated 3D Object Discovery and Reconstruction
18. CVPR 2023BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
19. CVPR 2023Balanced Spherical Grid for Egocentric View Synthesis
20. CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
21. CVPR 2023Behind the Scenes: Density Fields for Single View Reconstruction
22. CVPR 2023Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
23. CVPR 2023Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
24. CVPR 2023BiFormer: Vision Transformer With Bi-Level Routing Attention
25. CVPR 2023Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
26. CVPR 2023Boost Vision Transformer With GPU-Friendly Sparsity and Quantization
27. CVPR 2023BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration
28. CVPR 2023Building Rearticulable Models for Arbitrary 3D Objects From 4D Point Clouds
29. CVPR 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
30. CVPR 2023BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image
31. CVPR 2023Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction
32. CVPR 2023Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields
33. CVPR 2023CAP: Robust Point Cloud Classification via Semantic and Structural Modeling
34. CVPR 2023Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
35. CVPR 2023CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions
36. CVPR 2023CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data
37. CVPR 2023CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP
38. CVPR 2023Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories
39. CVPR 2023Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning
40. CVPR 2023CompletionFormer: Depth Completion With Convolutions and Vision Transformers
41. CVPR 2023Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
42. CVPR 2023Consistent View Synthesis With Pose-Guided Diffusion Models
43. CVPR 2023ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning
44. CVPR 2023CP3: Channel Pruning Plug-In for Point-Based Networks
45. CVPR 2023Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis
46. CVPR 2023CXTrack: Improving 3D Point Cloud Tracking With Contextual Information
47. CVPR 2023DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model
48. CVPR 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields
49. CVPR 2023DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking
50. CVPR 2023Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

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。