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 3 / 5 页

  1. ICML 2026Streaming Sliced Optimal Transport
  2. ICML 2026Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular Video
  3. ICML 2026The Extra Tokens Matter: Disentangled Representation Learning with Vision Transformers
  4. ICML 2026TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
  5. ICML 2026TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
  6. ICML 2026TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding
  7. ICML 2026Towards Docking-oriented De Novo Ligand Design via Gradient Inversion
  8. ICML 2026Towards Scalable and Consistent 3D Editing
  9. ICML 2026Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
  10. ICML 2026TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
  11. ICML 2026TVDRNet: Text-driven Viewpoint Optimization via Differentiable Rendering for 3D Reasoning Segmentation
  12. ICML 2026Utonia: Toward One Encoder for All Point Clouds
  13. ICML 2026VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
  14. ICML 2026Vision Transformer Finetuning Benefits from Non-Smooth Components
  15. ICML 2026WhisperSplat: Lossless Steganography in 3D Gaussian Splatting
  16. ICML 2026WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
  17. ICML 2026Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation
  18. ICML 20253D Question Answering via only 2D Vision-Language Models
  19. ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
  20. ICML 2025An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
  21. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
  22. ICML 2025Compositional Generalization via Forced Rendering of Disentangled Latents
  23. ICML 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
  24. ICML 2025CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
  25. ICML 2025CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
  26. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
  27. ICML 2025Efficient LiDAR Reflectance Compression via Scanning Serialization
  28. ICML 2025Enhancing Visual Localization with Cross-Domain Image Generation
  29. ICML 2025ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
  30. ICML 2025Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
  31. ICML 2025ExtPose: Robust and Coherent Pose Estimation by Extending ViTs
  32. ICML 2025Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
  33. ICML 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
  34. ICML 2025Generative Point Cloud Registration
  35. ICML 2025Geometric Algebra Planes: Convex Implicit Neural Volumes
  36. ICML 2025Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
  37. ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
  38. ICML 2025History-Guided Video Diffusion
  39. ICML 2025HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
  40. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
  41. ICML 2025Layer by Layer: Uncovering Hidden Representations in Language Models
  42. ICML 2025Learning Vision and Language Concepts for Controllable Image Generation
  43. ICML 2025MiraGe: Editable 2D Images using Gaussian Splatting
  44. ICML 2025MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification
  45. ICML 2025One-dimensional Path Convolution
  46. ICML 2025Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
  47. ICML 2025Oscillation-Reduced MXFP4 Training for Vision Transformers
  48. ICML 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
  49. ICML 2025PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
  50. ICML 2025PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning

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