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 751 篇，第 14 / 16 页

  1. NeurIPS 2024LION: Linear Group RNN for 3D Object Detection in Point Clouds
  2. NeurIPS 2024LiT: Unifying LiDAR "Languages" with LiDAR Translator
  3. NeurIPS 2024LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering
  4. NeurIPS 2024LLaNA: Large Language and NeRF Assistant
  5. NeurIPS 2024LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
  6. NeurIPS 2024LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
  7. NeurIPS 2024LP-3DGS: Learning to Prune 3D Gaussian Splatting
  8. NeurIPS 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Data
  9. NeurIPS 2024Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
  10. NeurIPS 2024LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
  11. NeurIPS 2024Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
  12. NeurIPS 2024Memorize What Matters: Emergent Scene Decomposition from Multitraverse
  13. NeurIPS 2024MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
  14. NeurIPS 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
  15. NeurIPS 2024MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes
  16. NeurIPS 2024Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
  17. NeurIPS 2024Mixture of neural fields for heterogeneous reconstruction in cryo-EM
  18. NeurIPS 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
  19. NeurIPS 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
  20. NeurIPS 2024Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
  21. NeurIPS 2024Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
  22. NeurIPS 2024Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction
  23. NeurIPS 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
  24. NeurIPS 2024Multiview Scene Graph
  25. NeurIPS 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
  26. NeurIPS 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
  27. NeurIPS 2024MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps
  28. NeurIPS 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
  29. NeurIPS 2024NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics
  30. NeurIPS 2024Neural Gaffer: Relighting Any Object via Diffusion
  31. NeurIPS 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
  32. NeurIPS 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
  33. NeurIPS 2024NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
  34. NeurIPS 2024Nonparametric Regression for 3D Point Cloud Learning
  35. NeurIPS 2024Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
  36. NeurIPS 2024OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
  37. NeurIPS 2024OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
  38. NeurIPS 2024ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
  39. NeurIPS 2024One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
  40. NeurIPS 2024OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
  41. NeurIPS 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
  42. NeurIPS 2024OPUS: Occupancy Prediction Using a Sparse Set
  43. NeurIPS 2024PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
  44. NeurIPS 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
  45. NeurIPS 2024Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
  46. NeurIPS 2024PhyRecon: Physically Plausible Neural Scene Reconstruction
  47. NeurIPS 2024Physically Compatible 3D Object Modeling from a Single Image
  48. NeurIPS 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
  49. NeurIPS 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis
  50. NeurIPS 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

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