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 839 篇，第 10 / 17 页

  1. NeurIPS 2025ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
  2. NeurIPS 2025Video Perception Models for 3D Scene Synthesis
  3. NeurIPS 2025Vision Transformers with Self-Distilled Registers
  4. NeurIPS 2025ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning
  5. NeurIPS 2025Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
  6. NeurIPS 2025VividFace: A Robost and High-Fidelity Video Face Swapping Framework
  7. NeurIPS 2025VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
  8. NeurIPS 2025Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
  9. NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
  10. NeurIPS 2025What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
  11. NeurIPS 2025When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
  12. NeurIPS 2025WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild
  13. NeurIPS 2025X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
  14. NeurIPS 2025ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
  15. NeurIPS 2025ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
  16. NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
  17. NeurIPS 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
  18. NeurIPS 20243D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
  19. NeurIPS 20243D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
  20. NeurIPS 20243D Gaussian Splatting as Markov Chain Monte Carlo
  21. NeurIPS 20243DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
  22. NeurIPS 20243DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
  23. NeurIPS 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
  24. NeurIPS 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
  25. NeurIPS 20244Diffusion: Multi-view Video Diffusion Model for 4D Generation
  26. NeurIPS 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
  27. NeurIPS 2024A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
  28. NeurIPS 2024A General Protocol to Probe Large Vision Models for 3D Physical Understanding
  29. NeurIPS 2024A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
  30. NeurIPS 2024A Unified Framework for 3D Scene Understanding
  31. NeurIPS 2024AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
  32. NeurIPS 2024Any2Policy: Learning Visuomotor Policy with Any-Modality
  33. NeurIPS 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
  34. NeurIPS 2024Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
  35. NeurIPS 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
  36. NeurIPS 2024AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
  37. NeurIPS 2024Benchmarking the Attribution Quality of Vision Models
  38. NeurIPS 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
  39. NeurIPS 2024BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
  40. NeurIPS 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models
  41. NeurIPS 2024Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
  42. NeurIPS 2024Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
  43. NeurIPS 2024Coherent 3D Scene Diffusion From a Single RGB Image
  44. NeurIPS 2024ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
  45. NeurIPS 2024ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
  46. NeurIPS 2024CRAYM: Neural Field Optimization via Camera RAY Matching
  47. NeurIPS 2024CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM
  48. NeurIPS 2024CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
  49. NeurIPS 2024D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
  50. NeurIPS 2024DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos

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