三维视觉论文趋势 2023–2026

三维重建与神经渲染

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,226 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

三维视觉论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231525622333563
20242229644389751
202525416252434902
20262111971174851,010

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

全部三维视觉论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 751 篇，第 11 / 16 页

  1. ICML 2024HyperFields: Towards Zero-Shot Generation of NeRFs from Text
  2. ICML 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
  3. ICML 2024Improving Interpretation Faithfulness for Vision Transformers
  4. ICML 2024Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
  5. ICML 2024Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
  6. ICML 2024Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
  7. ICML 2024Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
  8. ICML 2024Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers
  9. ICML 2024Neural NeRF Compression
  10. ICML 2024NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors
  11. ICML 2024NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction
  12. ICML 2024OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
  13. ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
  14. ICML 2024Outlier-aware Slicing for Post-Training Quantization in Vision Transformer
  15. ICML 2024PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques
  16. ICML 2024Position: Do Not Explain Vision Models Without Context
  17. ICML 2024Positive Concave Deep Equilibrium Models
  18. ICML 2024Profile Reconstruction from Private Sketches
  19. ICML 2024PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
  20. ICML 2024Robust Inverse Graphics via Probabilistic Inference
  21. ICML 2024S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
  22. ICML 2024Statistical Test for Attention Maps in Vision Transformers
  23. ICML 2024Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
  24. ICML 2024Toward Availability Attacks in 3D Point Clouds
  25. ICML 2024TVE: Learning Meta-attribution for Transferable Vision Explainer
  26. ICML 2024VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
  27. ICML 2024Vision Transformers as Probabilistic Expansion from Learngene
  28. ICML 2024Weisfeiler Leman for Euclidean Equivariant Machine Learning
  29. ICML 2024When Will Gradient Regularization Be Harmful?
  30. NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
  31. NeurIPS 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
  32. NeurIPS 20243D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
  33. NeurIPS 20243D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
  34. NeurIPS 20243D Gaussian Splatting as Markov Chain Monte Carlo
  35. NeurIPS 20243DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
  36. NeurIPS 20243DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
  37. NeurIPS 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
  38. NeurIPS 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
  39. NeurIPS 20244Diffusion: Multi-view Video Diffusion Model for 4D Generation
  40. NeurIPS 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
  41. NeurIPS 2024A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
  42. NeurIPS 2024A General Protocol to Probe Large Vision Models for 3D Physical Understanding
  43. NeurIPS 2024A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
  44. NeurIPS 2024A Unified Framework for 3D Scene Understanding
  45. NeurIPS 2024AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
  46. NeurIPS 2024Any2Policy: Learning Visuomotor Policy with Any-Modality
  47. NeurIPS 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
  48. NeurIPS 2024Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
  49. NeurIPS 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
  50. NeurIPS 2024AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查三维视觉在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "3d-vision"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「计算机视觉」下的其他主题