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 6 / 16 页

  1. CVPR 2024NTO3D: Neural Target Object 3D Reconstruction with Segment Anything
  2. CVPR 2024NViST: In the Wild New View Synthesis from a Single Image with Transformers
  3. CVPR 2024OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
  4. CVPR 2024Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
  5. CVPR 2024Objects as Volumes: A Stochastic Geometry View of Opaque Solids
  6. CVPR 2024ODIN: A Single Model for 2D and 3D Segmentation
  7. CVPR 2024OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
  8. CVPR 2024On Scaling Up a Multilingual Vision and Language Model
  9. CVPR 2024On the Faithfulness of Vision Transformer Explanations
  10. CVPR 2024On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
  11. CVPR 2024Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
  12. CVPR 2024OneFormer3D: One Transformer for Unified Point Cloud Segmentation
  13. CVPR 2024OneLLM: One Framework to Align All Modalities with Language
  14. CVPR 2024OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
  15. CVPR 2024Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
  16. CVPR 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
  17. CVPR 2024PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video
  18. CVPR 2024PAPR in Motion: Seamless Point-level 3D Scene Interpolation
  19. CVPR 2024PaReNeRF: Toward Fast Large-scale Dynamic NeRF with Patch-based Reference
  20. CVPR 2024PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation
  21. CVPR 2024Perceptual Assessment and Optimization of HDR Image Rendering
  22. CVPR 2024Physical Property Understanding from Language-Embedded Feature Fields
  23. CVPR 2024Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models
  24. CVPR 2024PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
  25. CVPR 2024pix2gestalt: Amodal Segmentation by Synthesizing Wholes
  26. CVPR 2024pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
  27. CVPR 2024PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
  28. CVPR 2024PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
  29. CVPR 2024Point Cloud Pre-training with Diffusion Models
  30. CVPR 2024Point Transformer V3: Simpler Faster Stronger
  31. CVPR 2024PointInfinity: Resolution-Invariant Point Diffusion Models
  32. CVPR 2024Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts
  33. CVPR 2024PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates
  34. CVPR 2024Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data
  35. CVPR 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
  36. CVPR 2024Pre-training Vision Models with Mandelbulb Variations
  37. CVPR 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
  38. CVPR 2024Projecting Trackable Thermal Patterns for Dynamic Computer Vision
  39. CVPR 2024PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
  40. CVPR 2024QUADify: Extracting Meshes with Pixel-level Details and Materials from Images
  41. CVPR 2024R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization
  42. CVPR 2024Random Entangled Tokens for Adversarially Robust Vision Transformer
  43. CVPR 2024Real-time 3D-aware Portrait Video Relighting
  44. CVPR 2024ReconFusion: 3D Reconstruction with Diffusion Priors
  45. CVPR 2024Reconstructing Hands in 3D with Transformers
  46. CVPR 2024Reconstruction-free Cascaded Adaptive Compressive Sensing
  47. CVPR 2024RegionGPT: Towards Region Understanding Vision Language Model
  48. CVPR 2024RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method
  49. CVPR 2024RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation
  50. CVPR 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentation

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