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 16 / 19 页

  1. NeurIPS 2025HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
  2. NeurIPS 2025HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
  3. NeurIPS 2025I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
  4. NeurIPS 2025IBGS: Image-Based Gaussian Splatting
  5. NeurIPS 2025Implicit Modeling for Transferability Estimation of Vision Foundation Models
  6. NeurIPS 2025Improving Deep Learning for Accelerated MRI With Data Filtering
  7. NeurIPS 2025IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants
  8. NeurIPS 2025InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
  9. NeurIPS 2025InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
  10. NeurIPS 2025Instant4D: 4D Gaussian Splatting in Minutes
  11. NeurIPS 2025Interpreting vision transformers via residual replacement model
  12. NeurIPS 2025IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
  13. NeurIPS 2025Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model
  14. NeurIPS 2025Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding
  15. NeurIPS 2025KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing
  16. NeurIPS 2025L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery
  17. NeurIPS 2025LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
  18. NeurIPS 2025Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields
  19. NeurIPS 2025Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting
  20. NeurIPS 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
  21. NeurIPS 2025Learning Generalizable Shape Completion with SIM(3) Equivariance
  22. NeurIPS 2025Learning Neural Exposure Fields for View Synthesis
  23. NeurIPS 2025Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
  24. NeurIPS 2025Linearly Constrained Diffusion Implicit Models
  25. NeurIPS 2025LinPrim: Linear Primitives for Differentiable Volumetric Rendering
  26. NeurIPS 2025LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans
  27. NeurIPS 2025LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
  28. NeurIPS 2025MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference
  29. NeurIPS 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
  30. NeurIPS 2025MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
  31. NeurIPS 2025Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
  32. NeurIPS 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans
  33. NeurIPS 2025MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction
  34. NeurIPS 2025Model Editing for Vision Transformers
  35. NeurIPS 2025Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow
  36. NeurIPS 2025Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
  37. NeurIPS 2025Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
  38. NeurIPS 2025MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
  39. NeurIPS 2025MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
  40. NeurIPS 2025Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
  41. NeurIPS 2025NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
  42. NeurIPS 2025Neural Green’s Functions
  43. NeurIPS 2025NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods
  44. NeurIPS 2025Non-Line-of-Sight 3D Reconstruction with Radar
  45. NeurIPS 2025NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input
  46. NeurIPS 2025Normalize Filters! Classical Wisdom for Deep Vision
  47. NeurIPS 2025Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
  48. NeurIPS 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
  49. NeurIPS 2025Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
  50. NeurIPS 2025ODG: Occupancy Prediction Using Dual Gaussians

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