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 3,224 篇，第 33 / 65 页

  1. ICLR 2025VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
  2. ICLR 2025Vision and Language Synergy for Rehearsal Free Continual Learning
  3. ICLR 2025What's the Move? Hybrid Imitation Learning via Salient Points
  4. ICLR 2025Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
  5. ICML 20253D Question Answering via only 2D Vision-Language Models
  6. ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
  7. ICML 2025An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
  8. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
  9. ICML 2025Compositional Generalization via Forced Rendering of Disentangled Latents
  10. ICML 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
  11. ICML 2025CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
  12. ICML 2025CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
  13. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
  14. ICML 2025Efficient LiDAR Reflectance Compression via Scanning Serialization
  15. ICML 2025Enhancing Visual Localization with Cross-Domain Image Generation
  16. ICML 2025ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
  17. ICML 2025Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
  18. ICML 2025ExtPose: Robust and Coherent Pose Estimation by Extending ViTs
  19. ICML 2025Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
  20. ICML 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
  21. ICML 2025Generative Point Cloud Registration
  22. ICML 2025Geometric Algebra Planes: Convex Implicit Neural Volumes
  23. ICML 2025Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
  24. ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
  25. ICML 2025History-Guided Video Diffusion
  26. ICML 2025HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
  27. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
  28. ICML 2025Layer by Layer: Uncovering Hidden Representations in Language Models
  29. ICML 2025Learning Vision and Language Concepts for Controllable Image Generation
  30. ICML 2025MiraGe: Editable 2D Images using Gaussian Splatting
  31. ICML 2025MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification
  32. ICML 2025One-dimensional Path Convolution
  33. ICML 2025Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
  34. ICML 2025Oscillation-Reduced MXFP4 Training for Vision Transformers
  35. ICML 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
  36. ICML 2025PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
  37. ICML 2025PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning
  38. ICML 2025Point Cloud Dataset Distillation
  39. ICML 2025Point-Level Topological Representation Learning on Point Clouds
  40. ICML 2025Position: You Can't Manufacture a NeRF
  41. ICML 2025Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
  42. ICML 2025Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures
  43. ICML 2025ReferSplat: Referring Segmentation in 3D Gaussian Splatting
  44. ICML 2025RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
  45. ICML 2025Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
  46. ICML 2025Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
  47. ICML 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
  48. ICML 2025Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
  49. ICML 2025Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes
  50. ICML 2025Symmetry-Robust 3D Orientation Estimation

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