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 15 / 65 页

  1. ICML 2026DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
  2. ICML 2026DSGCR: Decomposed Spectral Geometry-Aware Cross-Modal Semantic Representation for 3D Visual Grounding
  3. ICML 2026DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
  4. ICML 2026Elastic Diffusion Transformer
  5. ICML 2026EnerGS: Energy-Based Gaussian Splatting under Partial Geometric Priors
  6. ICML 2026EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
  7. ICML 2026Equivariant Latent Alignment via Flow Matching under Group Symmetries
  8. ICML 2026Equivariant Neural Networks for General Linear Symmetries on Lie Algebras
  9. ICML 2026Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range
  10. ICML 2026Fast-SAM3D: 3Dfy Anything in Images but Faster
  11. ICML 2026FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
  12. ICML 2026FlowCloud: Learning Continuous Spatiotemporal Dynamics from Unpaired Sparse Point Cloud Snapshots
  13. ICML 2026Focusing: View-Consistent Sparse Voxels for Efficient 3D VAE Training
  14. ICML 2026Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
  15. ICML 2026From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic Segmentation
  16. ICML 2026FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated Depth
  17. ICML 2026Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
  18. ICML 2026G$^2$TAM: Geometry Grounded Track Anything Model
  19. ICML 2026GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
  20. ICML 2026GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
  21. ICML 2026GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM Reasoning
  22. ICML 2026Geometric Collapse: When Vision Models Fail to Verify Physical Causality
  23. ICML 2026GeoMoLa: Geometry-Aware Motion Latents for Learning Robust Manipulation Policies
  24. ICML 2026GHOST: Geometry-Guided Hallucination of Opaque Surface Textures
  25. ICML 2026Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation
  26. ICML 2026Global Geometry Is Not Enough for Vision Representations
  27. ICML 2026GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
  28. ICML 2026GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
  29. ICML 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
  30. ICML 2026Improving Explicit Dynamic Gaussian Splatting Optimization via Update Mixture
  31. ICML 2026Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
  32. ICML 2026LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
  33. ICML 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
  34. ICML 2026LAVA: A Unified Framework for Finetuning Language and Vision Models
  35. ICML 2026Learning 3D-Gaussian Simulators from RGB Videos
  36. ICML 2026Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation
  37. ICML 2026Linearizing Vision Transformer with Test-Time Training
  38. ICML 2026MAC-NeRF: Motion-Aware Curriculum Learning for Dynamic LiDAR NeRFs
  39. ICML 2026Metric—Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
  40. ICML 2026Multi-Label Learning with Contrastive Cluster Self-Supervision for 3D Hierarchical Semantic Segmentation
  41. ICML 2026Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention
  42. ICML 2026Optimizing Rank for High-Fidelity Implicit Neural Representations
  43. ICML 2026PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
  44. ICML 2026PCGS: Deblurring 3D Gaussian Splatting with Patch Comparison
  45. ICML 2026Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Spectral Super-Resolution for Snapshot Compressive Imaging
  46. ICML 2026PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
  47. ICML 2026Physics-Informed Pre-training on Efficient Electron-Density Images for Organic Material Property Prediction
  48. ICML 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification
  49. ICML 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
  50. ICML 2026Prototype-Based Test-Time Adaptation of Vision-Language Models

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