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 902 篇，第 4 / 19 页

  1. CVPR 2025GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency
  2. CVPR 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
  3. CVPR 2025Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals
  4. CVPR 2025Generating 3D-Consistent Videos from Unposed Internet Photos
  5. CVPR 2025Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision
  6. CVPR 2025Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction
  7. CVPR 2025Generative Gaussian Splatting for Unbounded 3D City Generation
  8. CVPR 2025Generative Hard Example Augmentation for Semantic Point Cloud Segmentation
  9. CVPR 2025Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation
  10. CVPR 2025Generative Sparse-View Gaussian Splatting
  11. CVPR 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videos
  12. CVPR 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors
  13. CVPR 2025GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos
  14. CVPR 2025Geometry Field Splatting with Gaussian Surfels
  15. CVPR 2025Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency
  16. CVPR 2025GIFStream: 4D Gaussian-based Immersive Video with Feature Stream
  17. CVPR 2025Glossy Object Reconstruction with Cost-effective Polarized Acquisition
  18. CVPR 2025GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector
  19. CVPR 2025GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
  20. CVPR 2025GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections
  21. CVPR 2025GPVK-VL: Geometry-Preserving Virtual Keyframes for Visual Localization under Large Viewpoint Changes
  22. CVPR 2025Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision
  23. CVPR 2025GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning
  24. CVPR 2025Gromov-Wasserstein Problem with Cyclic Symmetry
  25. CVPR 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
  26. CVPR 2025GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking
  27. CVPR 2025GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
  28. CVPR 2025HandOS: 3D Hand Reconstruction in One Stage
  29. CVPR 2025Hardware-Rasterized Ray-Based Gaussian Splatting
  30. CVPR 2025Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
  31. CVPR 2025Hash3D: Training-free Acceleration for 3D Generation
  32. CVPR 2025HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration
  33. CVPR 2025HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars
  34. CVPR 2025Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation
  35. CVPR 2025High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
  36. CVPR 2025High-Fidelity Lightweight Mesh Reconstruction from Point Clouds
  37. CVPR 2025High-quality Point Cloud Oriented Normal Estimation via Hybrid Angular and Euclidean Distance Encoding
  38. CVPR 2025HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving
  39. CVPR 2025HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
  40. CVPR 2025HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
  41. CVPR 2025Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
  42. CVPR 2025HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
  43. CVPR 2025HRAvatar: High-Quality and Relightable Gaussian Head Avatar
  44. CVPR 2025HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
  45. CVPR 2025Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
  46. CVPR 2025Hypergraph Vision Transformers: Images are More than Nodes, More than Edges
  47. CVPR 2025HyperGS: Hyperspectral 3D Gaussian Splatting
  48. CVPR 2025IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments
  49. CVPR 2025Identity-preserving Distillation Sampling by Fixed-Point Iterator
  50. CVPR 2025iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting

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