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 254 篇，第 5 / 6 页

  1. NeurIPS 2025Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
  2. NeurIPS 2025SegMASt3R: Geometry Grounded Segment Matching
  3. NeurIPS 2025Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting
  4. NeurIPS 2025SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation
  5. NeurIPS 2025Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
  6. NeurIPS 2025SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
  7. NeurIPS 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling
  8. NeurIPS 2025SpatialLM: Training Large Language Models for Structured Indoor Modeling
  9. NeurIPS 2025Spatially-aware Weights Tokenization for NeRF-Language Models
  10. NeurIPS 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
  11. NeurIPS 2025Spik-NeRF: Spiking Neural Networks for Neural Radiance Fields
  12. NeurIPS 2025Spike4DGS: Towards High-Speed Dynamic Scene Rendering with 4D Gaussian Splatting via a Spike Camera Array
  13. NeurIPS 2025Spiking Neural Networks Need High-Frequency Information
  14. NeurIPS 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
  15. NeurIPS 2025SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes
  16. NeurIPS 2025Structured Initialization for Vision Transformers
  17. NeurIPS 2025Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles
  18. NeurIPS 2025SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
  19. NeurIPS 2025SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
  20. NeurIPS 2025Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting
  21. NeurIPS 2025Test3R: Learning to Reconstruct 3D at Test Time
  22. NeurIPS 2025TGA: True-to-Geometry Avatar Dynamic Reconstruction
  23. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
  24. NeurIPS 2025Token Embeddings Violate the Manifold Hypothesis
  25. NeurIPS 2025Topology-Aware Learning of Tubular Manifolds via SE(3)-Equivariant Network on Ball B-Spline Curve
  26. NeurIPS 2025Towards 3D Objectness Learning in an Open World
  27. NeurIPS 2025Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery
  28. NeurIPS 2025TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
  29. NeurIPS 2025TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
  30. NeurIPS 2025TreeSplat: Mergeable Tree for Deformable Gaussian Splatting
  31. NeurIPS 2025TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming
  32. NeurIPS 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching
  33. NeurIPS 2025UFM: A Simple Path towards Unified Dense Correspondence with Flow
  34. NeurIPS 2025UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
  35. NeurIPS 2025Under the Shadow: Exploiting Opacity Variation for Fine-grained Shadow Detection
  36. NeurIPS 2025Understanding while Exploring: Semantics-driven Active Mapping
  37. NeurIPS 2025Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting
  38. NeurIPS 2025URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
  39. NeurIPS 2025VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
  40. NeurIPS 2025ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
  41. NeurIPS 2025Video Perception Models for 3D Scene Synthesis
  42. NeurIPS 2025Vision Transformers with Self-Distilled Registers
  43. NeurIPS 2025ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning
  44. NeurIPS 2025Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
  45. NeurIPS 2025VividFace: A Robost and High-Fidelity Video Face Swapping Framework
  46. NeurIPS 2025VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
  47. NeurIPS 2025Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
  48. NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
  49. NeurIPS 2025What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
  50. NeurIPS 2025When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

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