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 12 / 65 页

  1. ICLR 2026From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
  2. ICLR 2026From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
  3. ICLR 2026From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting
  4. ICLR 2026Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
  5. ICLR 2026G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
  6. ICLR 2026GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation
  7. ICLR 2026GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
  8. ICLR 2026GOLDILOCS: GENERAL OBJECT-LEVEL DETECTION AND LABELING OF CHANGES IN SCENES
  9. ICLR 2026GOOD: Geometry-guided Out-of-Distribution Modeling for Open-set Test-time Adaptation in Point Cloud Semantic Segmentation
  10. ICLR 2026GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
  11. ICLR 2026Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
  12. ICLR 2026Guaranteed Simply Connected Mesh Reconstruction from an Unorganized Point Cloud
  13. ICLR 2026HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-K
  14. ICLR 2026Horseshoe Splatting: Handling Structural Sparsity for Uncertainty-Aware Gaussian-Splatting Radiance Field Rendering
  15. ICLR 2026HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image Detection
  16. ICLR 2026Human3R: Everyone Everywhere All at Once
  17. ICLR 2026Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of High-resolution Images
  18. ICLR 2026IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
  19. ICLR 2026Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame Displacements
  20. ICLR 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter‑Slice Consistent Stochasticity
  21. ICLR 2026IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction
  22. ICLR 2026Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps
  23. ICLR 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
  24. ICLR 2026Learning Unified Representation of 3D Gaussian Splatting
  25. ICLR 2026Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
  26. ICLR 2026LiTo: Surface Light Field Tokenization
  27. ICLR 2026Locality-Attending Vision Transformer
  28. ICLR 2026Low-Latency Neural LiDAR Compression with 2D Context Models
  29. ICLR 2026LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
  30. ICLR 2026Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
  31. ICLR 2026Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting
  32. ICLR 2026MEGS^{2}: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning
  33. ICLR 2026Mesh Splatting for End-to-end Multiview Surface Reconstruction
  34. ICLR 2026Mobile-GS: Real-time Gaussian Splatting for Mobile Devices
  35. ICLR 2026MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
  36. ICLR 2026MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow Matching
  37. ICLR 2026Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
  38. ICLR 2026MotionGPT3: Human Motion as a Second Modality
  39. ICLR 2026Neural Compression of 3D Meshes using Sparse Implicit Representation
  40. ICLR 2026NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting
  41. ICLR 2026NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
  42. ICLR 2026ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
  43. ICLR 2026On the Generalization Capacities of MLLMs for Spatial Intelligence
  44. ICLR 2026On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition
  45. ICLR 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
  46. ICLR 2026Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
  47. ICLR 2026OpenFly: A COMPREHENSIVE PLATFORM FOR AERIAL VISION-LANGUAGE NAVIGATION
  48. ICLR 2026ORCaS: Unsupervised Depth Completion via Occluded Region Completion as Supervision
  49. ICLR 2026OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction
  50. ICLR 2026PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception

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