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 2 / 19 页

  1. CVPR 2025Coherent 3D Portrait Video Reconstruction via Triplane Fusion
  2. CVPR 2025ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration
  3. CVPR 2025CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
  4. CVPR 2025CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
  5. CVPR 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
  6. CVPR 2025Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph
  7. CVPR 2025Continuous 3D Perception Model with Persistent State
  8. CVPR 2025Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting
  9. CVPR 2025Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion
  10. CVPR 2025CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
  11. CVPR 2025CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
  12. CVPR 2025D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.
  13. CVPR 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  14. CVPR 2025DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
  15. CVPR 2025DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
  16. CVPR 2025DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis
  17. CVPR 2025Deformable Radial Kernel Splatting
  18. CVPR 2025Dense-SfM: Structure from Motion with Dense Consistent Matching
  19. CVPR 2025Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
  20. CVPR 2025DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
  21. CVPR 2025DepthSplat: Connecting Gaussian Splatting and Depth
  22. CVPR 2025DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
  23. CVPR 2025DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
  24. CVPR 2025DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting
  25. CVPR 2025Differentiable Inverse Rendering with Interpretable Basis BRDFs
  26. CVPR 2025DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement
  27. CVPR 2025DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
  28. CVPR 2025Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset
  29. CVPR 2025DIO: Decomposable Implicit 4D Occupancy-Flow World Model
  30. CVPR 2025DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation
  31. CVPR 2025Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
  32. CVPR 2025DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting
  33. CVPR 2025DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal
  34. CVPR 2025Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
  35. CVPR 2025Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration
  36. CVPR 2025DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
  37. CVPR 2025DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
  38. CVPR 2025DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting
  39. CVPR 2025DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
  40. CVPR 2025DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
  41. CVPR 2025Dual Focus-Attention Transformer for Robust Point Cloud Registration
  42. CVPR 2025DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
  43. CVPR 2025DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features
  44. CVPR 2025DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition
  45. CVPR 2025DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes
  46. CVPR 2025EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction
  47. CVPR 2025EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
  48. CVPR 2025EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features
  49. CVPR 2025EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
  50. CVPR 2025Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression

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