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 51 / 65 页

  1. NeurIPS 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
  2. NeurIPS 2024Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
  3. NeurIPS 2024Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
  4. NeurIPS 2024Fast Encoder-Based 3D from Casual Videos via Point Track Processing
  5. NeurIPS 2024FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
  6. NeurIPS 2024FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
  7. NeurIPS 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
  8. NeurIPS 2024FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
  9. NeurIPS 2024Flatten Anything: Unsupervised Neural Surface Parameterization
  10. NeurIPS 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes
  11. NeurIPS 2024From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
  12. NeurIPS 2024From Chaos to Clarity: 3DGS in the Dark
  13. NeurIPS 2024Fully Explicit Dynamic Gaussian Splatting
  14. NeurIPS 2024Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
  15. NeurIPS 2024GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
  16. NeurIPS 2024GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
  17. NeurIPS 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
  18. NeurIPS 2024Generalizable and Animatable Gaussian Head Avatar
  19. NeurIPS 2024Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation
  20. NeurIPS 2024GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
  21. NeurIPS 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
  22. NeurIPS 2024GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
  23. NeurIPS 2024GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
  24. NeurIPS 2024Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting
  25. NeurIPS 2024GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
  26. NeurIPS 2024GS-Hider: Hiding Messages into 3D Gaussian Splatting
  27. NeurIPS 2024GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
  28. NeurIPS 2024GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
  29. NeurIPS 2024GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
  30. NeurIPS 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
  31. NeurIPS 2024Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
  32. NeurIPS 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
  33. NeurIPS 2024HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
  34. NeurIPS 2024Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
  35. NeurIPS 2024How to Use Diffusion Priors under Sparse Views?
  36. NeurIPS 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
  37. NeurIPS 2024Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
  38. NeurIPS 2024Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
  39. NeurIPS 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
  40. NeurIPS 2024ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
  41. NeurIPS 2024IllumiNeRF: 3D Relighting Without Inverse Rendering
  42. NeurIPS 2024Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
  43. NeurIPS 2024Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
  44. NeurIPS 2024In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
  45. NeurIPS 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
  46. NeurIPS 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?
  47. NeurIPS 2024Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
  48. NeurIPS 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
  49. NeurIPS 2024L4GM: Large 4D Gaussian Reconstruction Model
  50. NeurIPS 2024LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image

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