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 58 / 65 页

  1. CVPR 2023Neural Intrinsic Embedding for Non-Rigid Point Cloud Matching
  2. CVPR 2023Neural Kaleidoscopic Space Sculpting
  3. CVPR 2023Neural Kernel Surface Reconstruction
  4. CVPR 2023Neural Lens Modeling
  5. CVPR 2023Neuralangelo: High-Fidelity Neural Surface Reconstruction
  6. CVPR 2023NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds
  7. CVPR 2023NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views
  8. CVPR 2023NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation
  9. CVPR 2023NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation
  10. CVPR 2023NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
  11. CVPR 2023NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior
  12. CVPR 2023Normal-Guided Garment UV Prediction for Human Re-Texturing
  13. CVPR 2023Novel Class Discovery for 3D Point Cloud Semantic Segmentation
  14. CVPR 2023Novel-View Acoustic Synthesis
  15. CVPR 2023Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone?
  16. CVPR 2023Occlusion-Free Scene Recovery via Neural Radiance Fields
  17. CVPR 2023Octree Guided Unoriented Surface Reconstruction
  18. CVPR 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
  19. CVPR 2023On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks
  20. CVPR 2023One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field
  21. CVPR 2023Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework
  22. CVPR 2023Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation
  23. CVPR 2023ORCa: Glossy Objects As Radiance-Field Cameras
  24. CVPR 2023OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering
  25. CVPR 2023PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers
  26. CVPR 2023Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization
  27. CVPR 2023PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields
  28. CVPR 2023PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters
  29. CVPR 2023Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning
  30. CVPR 2023PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations
  31. CVPR 2023PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models
  32. CVPR 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
  33. CVPR 2023PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration
  34. CVPR 2023PersonNeRF: Personalized Reconstruction From Photo Collections
  35. CVPR 2023PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces
  36. CVPR 2023Physical-World Optical Adversarial Attacks on 3D Face Recognition
  37. CVPR 2023PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
  38. CVPR 2023PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering
  39. CVPR 2023Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting
  40. CVPR 2023Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields
  41. CVPR 2023PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees
  42. CVPR 2023PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering
  43. CVPR 2023PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos
  44. CVPR 2023PointConvFormer: Revenge of the Point-Based Convolution
  45. CVPR 2023PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
  46. CVPR 2023Pointersect: Neural Rendering With Cloud-Ray Intersection
  47. CVPR 2023PointListNet: Deep Learning on 3D Point Lists
  48. CVPR 2023PointVector: A Vector Representation in Point Cloud Analysis
  49. CVPR 2023Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once
  50. CVPR 2023Power Bundle Adjustment for Large-Scale 3D Reconstruction

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