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 563 篇，第 7 / 12 页

  1. CVPR 2023Teaching Structured Vision & Language Concepts to Vision & Language Models
  2. CVPR 2023Temporally Consistent Online Depth Estimation Using Point-Based Fusion
  3. CVPR 2023TensoIR: Tensorial Inverse Rendering
  4. CVPR 2023Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering
  5. CVPR 2023TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering
  6. CVPR 2023ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling
  7. CVPR 2023Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors
  8. CVPR 2023Trade-Off Between Robustness and Accuracy of Vision Transformers
  9. CVPR 2023Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization
  10. CVPR 2023Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization
  11. CVPR 2023TriVol: Point Cloud Rendering via Triple Volumes
  12. CVPR 2023TrojViT: Trojan Insertion in Vision Transformers
  13. CVPR 2023Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving
  14. CVPR 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
  15. CVPR 2023Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling
  16. CVPR 2023Unifying Vision, Text, and Layout for Universal Document Processing
  17. CVPR 2023Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving
  18. CVPR 2023Unsupervised Continual Semantic Adaptation Through Neural Rendering
  19. CVPR 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
  20. CVPR 2023Unsupervised Volumetric Animation
  21. CVPR 2023VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization
  22. CVPR 2023ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification
  23. CVPR 2023Vision Transformer With Super Token Sampling
  24. CVPR 2023Vision Transformers Are Good Mask Auto-Labelers
  25. CVPR 2023Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves
  26. CVPR 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud
  27. CVPR 2023VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
  28. CVPR 2023Weakly Supervised Monocular 3D Object Detection Using Multi-View Projection and Direction Consistency
  29. CVPR 2023What You Can Reconstruct From a Shadow
  30. CVPR 2023WildLight: In-the-Wild Inverse Rendering With a Flashlight
  31. CVPR 2023WIRE: Wavelet Implicit Neural Representations
  32. CVPR 2023You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?
  33. CVPR 2023You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
  34. ICLR 2023$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
  35. ICLR 20233D generation on ImageNet
  36. ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
  37. ICLR 2023Analogy-Forming Transformers for Few-Shot 3D Parsing
  38. ICLR 2023Bidirectional Propagation for Cross-Modal 3D Object Detection
  39. ICLR 2023Budgeted Training for Vision Transformer
  40. ICLR 2023Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens
  41. ICLR 2023CircNet: Meshing 3D Point Clouds with Circumcenter Detection
  42. ICLR 2023CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
  43. ICLR 2023CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
  44. ICLR 2023Conditional Positional Encodings for Vision Transformers
  45. ICLR 2023Cross-Layer Retrospective Retrieving via Layer Attention
  46. ICLR 2023Diagnosing and Rectifying Vision Models using Language
  47. ICLR 2023DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
  48. ICLR 2023DreamFusion: Text-to-3D using 2D Diffusion
  49. ICLR 2023EVA3D: Compositional 3D Human Generation from 2D Image Collections
  50. ICLR 2023Exploring Active 3D Object Detection from a Generalization Perspective

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