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 4 / 16 页

  1. CVPR 2024GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
  2. CVPR 2024Grounding and Enhancing Grid-based Models for Neural Fields
  3. CVPR 2024GS-IR: 3D Gaussian Splatting for Inverse Rendering
  4. CVPR 2024GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
  5. CVPR 2024GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
  6. CVPR 2024Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
  7. CVPR 2024H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration
  8. CVPR 2024HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud
  9. CVPR 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
  10. CVPR 2024HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting
  11. CVPR 2024HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
  12. CVPR 2024How Far Can We Compress Instant-NGP-Based NeRF?
  13. CVPR 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
  14. CVPR 2024HUGS: Human Gaussian Splats
  15. CVPR 2024Human Gaussian Splatting: Real-time Rendering of Animatable Avatars
  16. CVPR 2024HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
  17. CVPR 2024IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM
  18. CVPR 2024ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization
  19. CVPR 2024Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization
  20. CVPR 2024Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification
  21. CVPR 2024Inlier Confidence Calibration for Point Cloud Registration
  22. CVPR 2024InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields
  23. CVPR 2024Instance-Aware Group Quantization for Vision Transformers
  24. CVPR 2024Interactive3D: Create What You Want by Interactive 3D Generation
  25. CVPR 2024IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
  26. CVPR 2024Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields
  27. CVPR 2024IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images
  28. CVPR 2024IReNe: Instant Recoloring of Neural Radiance Fields
  29. CVPR 2024Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
  30. CVPR 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
  31. CVPR 2024Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
  32. CVPR 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
  33. CVPR 2024L-MAGIC: Language Model Assisted Generation of Images with Coherence
  34. CVPR 2024L0-Sampler: An L0 Model Guided Volume Sampling for NeRF
  35. CVPR 2024L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream
  36. CVPR 2024LangSplat: 3D Language Gaussian Splatting
  37. CVPR 2024Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding
  38. CVPR 2024Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates
  39. CVPR 2024Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans
  40. CVPR 2024Learning Correlation Structures for Vision Transformers
  41. CVPR 2024Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
  42. CVPR 2024Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes
  43. CVPR 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform
  44. CVPR 2024Learning Vision from Models Rivals Learning Vision from Data
  45. CVPR 2024Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency
  46. CVPR 2024LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes
  47. CVPR 2024LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis
  48. CVPR 2024LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes
  49. CVPR 2024LiSA: LiDAR Localization with Semantic Awareness
  50. CVPR 2024Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments

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