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 511 篇，第 3 / 11 页

  1. ICLR 2026Mobile-GS: Real-time Gaussian Splatting for Mobile Devices
  2. ICLR 2026MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
  3. ICLR 2026MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow Matching
  4. ICLR 2026Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
  5. ICLR 2026MotionGPT3: Human Motion as a Second Modality
  6. ICLR 2026Neural Compression of 3D Meshes using Sparse Implicit Representation
  7. ICLR 2026NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting
  8. ICLR 2026NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
  9. ICLR 2026ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
  10. ICLR 2026On the Generalization Capacities of MLLMs for Spatial Intelligence
  11. ICLR 2026On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition
  12. ICLR 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
  13. ICLR 2026Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
  14. ICLR 2026OpenFly: A COMPREHENSIVE PLATFORM FOR AERIAL VISION-LANGUAGE NAVIGATION
  15. ICLR 2026ORCaS: Unsupervised Depth Completion via Occluded Region Completion as Supervision
  16. ICLR 2026OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction
  17. ICLR 2026PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception
  18. ICLR 2026Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
  19. ICLR 2026Path Matters: Unveiling Geometric Implicit Bias via Curvature-Aware Sparse View Optimization
  20. ICLR 2026PD$^{2}$GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting
  21. ICLR 2026PEERING INTO THE UNKNOWN: ACTIVE VIEW SELECTION WITH NEURAL UNCERTAINTY MAPS FOR 3D RECONSTRUCTION
  22. ICLR 2026Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens
  23. ICLR 2026Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
  24. ICLR 2026Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
  25. ICLR 2026Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation
  26. ICLR 2026Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation
  27. ICLR 2026Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning
  28. ICLR 2026PointRePar : SpatioTemporal Point Relation Parsing for Robust Category-Unified 3D Tracking
  29. ICLR 2026PTNET: A PROPOSAL-CENTRIC TRANSFORMER NET- WORK FOR 3D OBJECT DETECTION
  30. ICLR 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
  31. ICLR 2026Quantized Visual Geometry Grounded Transformer
  32. ICLR 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
  33. ICLR 2026Radiometrically Consistent Gaussian Surfels for Inverse Rendering
  34. ICLR 2026RayI2P: Learning Rays for Image-to-Point Cloud Registration
  35. ICLR 2026ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
  36. ICLR 2026ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
  37. ICLR 2026Reliable Evaluation of MRI Motion Correction: Dataset and Insights
  38. ICLR 2026ReSplat: Degradation-agnostic Feed-forward Gaussian Splatting via Self-guided Residual Diffusion
  39. ICLR 2026Revisiting [CLS] and Patch Token Interaction in Vision Transformers
  40. ICLR 2026RoRE: Rotary Ray Embedding for Generalised Multi-Modal Scene Understanding
  41. ICLR 2026S2GO: Streaming Sparse Gaussian Occupancy
  42. ICLR 2026Scaling Sequence-to-Sequence Generative Neural Rendering
  43. ICLR 2026Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
  44. ICLR 2026Sharp Monocular View Synthesis in Less Than a Second
  45. ICLR 2026Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction
  46. ICLR 2026SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
  47. ICLR 2026SiNGER: A Clearer Voice Distills Vision Transformers Further
  48. ICLR 2026SkyEvents: A Large-Scale Event-enhanced UAV Dataset for Robust 3D Scene Reconstruction
  49. ICLR 2026Soft Equivariance Regularization for Invariant Self-Supervised Learning
  50. ICLR 2026SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

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