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 839 篇，第 14 / 17 页

  1. NeurIPS 2024SceneCraft: Layout-Guided 3D Scene Generation
  2. NeurIPS 2024SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
  3. NeurIPS 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
  4. NeurIPS 2024SE(3)-bi-equivariant Transformers for Point Cloud Assembly
  5. NeurIPS 2024Semi-Open 3D Object Retrieval via Hierarchical Equilibrium on Hypergraph
  6. NeurIPS 2024SfPUEL: Shape from Polarization under Unknown Environment Light
  7. NeurIPS 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
  8. NeurIPS 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
  9. NeurIPS 2024SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
  10. NeurIPS 2024Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
  11. NeurIPS 2024SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation
  12. NeurIPS 2024SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
  13. NeurIPS 2024STONE: A Submodular Optimization Framework for Active 3D Object Detection
  14. NeurIPS 2024Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
  15. NeurIPS 2024Subsurface Scattering for Gaussian Splatting
  16. NeurIPS 2024SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
  17. NeurIPS 2024TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
  18. NeurIPS 2024Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
  19. NeurIPS 2024Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
  20. NeurIPS 2024Tetrahedron Splatting for 3D Generation
  21. NeurIPS 2024TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
  22. NeurIPS 2024Toward Approaches to Scalability in 3D Human Pose Estimation
  23. NeurIPS 2024Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection
  24. NeurIPS 2024Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data
  25. NeurIPS 2024UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
  26. NeurIPS 2024UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
  27. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
  28. NeurIPS 2024USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
  29. NeurIPS 2024UV-free Texture Generation with Denoising and Geodesic Heat Diffusion
  30. NeurIPS 2024Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting
  31. NeurIPS 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
  32. NeurIPS 2024VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception
  33. NeurIPS 2024Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
  34. NeurIPS 2024Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
  35. NeurIPS 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
  36. NeurIPS 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
  37. NeurIPS 2024WildGaussians: 3D Gaussian Splatting In the Wild
  38. NeurIPS 2023[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
  39. NeurIPS 2023$p$-Poisson surface reconstruction in curl-free flow from point clouds
  40. NeurIPS 2023$SE(3)$ Equivariant Convolution and Transformer in Ray Space
  41. NeurIPS 20233D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
  42. NeurIPS 20233D Indoor Instance Segmentation in an Open-World
  43. NeurIPS 20233D-Aware Visual Question Answering about Parts, Poses and Occlusions
  44. NeurIPS 20233D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes
  45. NeurIPS 2023A Comprehensive Benchmark for Neural Human Radiance Fields
  46. NeurIPS 2023A Dataset of Relighted 3D Interacting Hands
  47. NeurIPS 2023A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions
  48. NeurIPS 2023AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
  49. NeurIPS 2023AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
  50. NeurIPS 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D 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