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 19 / 33 页

  1. CVPR 2025VGGT: Visual Geometry Grounded Transformer
  2. CVPR 2025Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
  3. CVPR 2025VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors
  4. CVPR 2025ViiNeuS: Volumetric Initialization for Implicit Neural Surface Reconstruction of Urban Scenes with Limited Image Overlap
  5. CVPR 2025Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes
  6. CVPR 2025Vision-Language Embodiment for Monocular Depth Estimation
  7. CVPR 2025VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
  8. CVPR 2025Volumetrically Consistent 3D Gaussian Rasterization
  9. CVPR 2025VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
  10. CVPR 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion
  11. CVPR 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
  12. CVPR 2025Wonderland: Navigating 3D Scenes from a Single Image
  13. CVPR 2025Yo'Chameleon: Personalized Vision and Language Generation
  14. CVPR 2025Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation
  15. CVPR 2025Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
  16. CVPR 2025Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model
  17. CVPR 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping
  18. CVPR 20243D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions
  19. CVPR 20243D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
  20. CVPR 20243D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis
  21. CVPR 20243D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
  22. CVPR 20243DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces
  23. CVPR 20243DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
  24. CVPR 20243DInAction: Understanding Human Actions in 3D Point Clouds
  25. CVPR 20244D Gaussian Splatting for Real-Time Dynamic Scene Rendering
  26. CVPR 20244K4D: Real-Time 4D View Synthesis at 4K Resolution
  27. CVPR 2024A Category Agnostic Model for Visual Rearrangment
  28. CVPR 2024A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling
  29. CVPR 2024A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization
  30. CVPR 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
  31. CVPR 2024A Subspace-Constrained Tyler's Estimator and its Applications to Structure from Motion
  32. CVPR 2024A Unified Framework for Human-centric Point Cloud Video Understanding
  33. CVPR 2024A Vision Check-up for Language Models
  34. CVPR 2024Active Prompt Learning in Vision Language Models
  35. CVPR 2024ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF
  36. CVPR 2024Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery
  37. CVPR 2024Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
  38. CVPR 2024AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
  39. CVPR 2024ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D Image
  40. CVPR 2024Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
  41. CVPR 2024Artist-Friendly Relightable and Animatable Neural Heads
  42. CVPR 2024ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering
  43. CVPR 2024Batch Normalization Alleviates the Spectral Bias in Coordinate Networks
  44. CVPR 2024Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
  45. CVPR 2024Bayesian Diffusion Models for 3D Shape Reconstruction
  46. CVPR 2024BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation
  47. CVPR 2024Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion
  48. CVPR 2024BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
  49. CVPR 2024BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
  50. CVPR 2024BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection

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