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 1,639 篇，第 14 / 33 页

  1. CVPR 2025GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector
  2. CVPR 2025GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
  3. CVPR 2025GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections
  4. CVPR 2025GPVK-VL: Geometry-Preserving Virtual Keyframes for Visual Localization under Large Viewpoint Changes
  5. CVPR 2025Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision
  6. CVPR 2025GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning
  7. CVPR 2025Gromov-Wasserstein Problem with Cyclic Symmetry
  8. CVPR 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
  9. CVPR 2025GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking
  10. CVPR 2025GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
  11. CVPR 2025HandOS: 3D Hand Reconstruction in One Stage
  12. CVPR 2025Hardware-Rasterized Ray-Based Gaussian Splatting
  13. CVPR 2025Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
  14. CVPR 2025Hash3D: Training-free Acceleration for 3D Generation
  15. CVPR 2025HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration
  16. CVPR 2025HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars
  17. CVPR 2025Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation
  18. CVPR 2025High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
  19. CVPR 2025High-Fidelity Lightweight Mesh Reconstruction from Point Clouds
  20. CVPR 2025High-quality Point Cloud Oriented Normal Estimation via Hybrid Angular and Euclidean Distance Encoding
  21. CVPR 2025HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving
  22. CVPR 2025HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
  23. CVPR 2025HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
  24. CVPR 2025Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
  25. CVPR 2025HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
  26. CVPR 2025HRAvatar: High-Quality and Relightable Gaussian Head Avatar
  27. CVPR 2025HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
  28. CVPR 2025Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
  29. CVPR 2025Hypergraph Vision Transformers: Images are More than Nodes, More than Edges
  30. CVPR 2025HyperGS: Hyperspectral 3D Gaussian Splatting
  31. CVPR 2025IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments
  32. CVPR 2025Identity-preserving Distillation Sampling by Fixed-Point Iterator
  33. CVPR 2025iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting
  34. CVPR 2025IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosC
  35. CVPR 2025Implicit Correspondence Learning for Image-to-Point Cloud Registration
  36. CVPR 2025Improving Gaussian Splatting with Localized Points Management
  37. CVPR 2025Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration
  38. CVPR 2025IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera
  39. CVPR 2025IndoorGS: Geometric Cues Guided Gaussian Splatting for Indoor Scene Reconstruction
  40. CVPR 2025InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
  41. CVPR 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting
  42. CVPR 2025Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects
  43. CVPR 2025InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
  44. CVPR 2025IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing
  45. CVPR 2025IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
  46. CVPR 2025Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video
  47. CVPR 2025L-SWAG: Layer-Sample Wise Activation with Gradients Information for Zero-Shot NAS on Vision Transformers
  48. CVPR 2025LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
  49. CVPR 2025Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking
  50. CVPR 2025Learning Partonomic 3D Reconstruction from Image Collections

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