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 235 篇，第 4 / 5 页

  1. ICML 2025Point Cloud Dataset Distillation
  2. ICML 2025Point-Level Topological Representation Learning on Point Clouds
  3. ICML 2025Position: You Can't Manufacture a NeRF
  4. ICML 2025Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
  5. ICML 2025Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures
  6. ICML 2025ReferSplat: Referring Segmentation in 3D Gaussian Splatting
  7. ICML 2025RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
  8. ICML 2025Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
  9. ICML 2025Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
  10. ICML 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
  11. ICML 2025Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
  12. ICML 2025Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes
  13. ICML 2025Symmetry-Robust 3D Orientation Estimation
  14. ICML 2025Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
  15. ICML 2025Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
  16. ICML 2025Unifying 2D and 3D Vision-Language Understanding
  17. ICML 2025Unpaired Point Cloud Completion via Unbalanced Optimal Transport
  18. ICML 2025VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
  19. ICML 2025You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
  20. ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
  21. ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
  22. ICML 2024A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
  23. ICML 2024An Explicit Frame Construction for Normalizing 3D Point Clouds
  24. ICML 2024Bridging Environments and Language with Rendering Functions and Vision-Language Models
  25. ICML 2024Careful with that Scalpel: Improving Gradient Surgery with an EMA
  26. ICML 2024COALA: A Practical and Vision-Centric Federated Learning Platform
  27. ICML 2024Coarse-To-Fine Tensor Trains for Compact Visual Representations
  28. ICML 2024Data-efficient Large Vision Models through Sequential Autoregression
  29. ICML 2024Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module
  30. ICML 2024ERQ: Error Reduction for Post-Training Quantization of Vision Transformers
  31. ICML 2024EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
  32. ICML 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
  33. ICML 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagation
  34. ICML 2024GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
  35. ICML 2024HyperFields: Towards Zero-Shot Generation of NeRFs from Text
  36. ICML 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
  37. ICML 2024Improving Interpretation Faithfulness for Vision Transformers
  38. ICML 2024Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
  39. ICML 2024Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
  40. ICML 2024Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
  41. ICML 2024Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
  42. ICML 2024Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers
  43. ICML 2024Neural NeRF Compression
  44. ICML 2024NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors
  45. ICML 2024NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction
  46. ICML 2024OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
  47. ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
  48. ICML 2024Outlier-aware Slicing for Post-Training Quantization in Vision Transformer
  49. ICML 2024PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques
  50. ICML 2024Position: Do Not Explain Vision Models Without Context

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