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 902 篇，第 17 / 19 页

  1. NeurIPS 2025Omnidirectional 3D Scene Reconstruction from Single Image
  2. NeurIPS 2025OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation
  3. NeurIPS 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
  4. NeurIPS 2025Online Segment Any 3D Thing as Instance Tracking
  5. NeurIPS 2025OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
  6. NeurIPS 2025OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
  7. NeurIPS 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
  8. NeurIPS 2025Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
  9. NeurIPS 2025Optimized Minimal 3D Gaussian Splatting
  10. NeurIPS 2025Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
  11. NeurIPS 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
  12. NeurIPS 2025PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting
  13. NeurIPS 2025PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors
  14. NeurIPS 2025Plenodium: Underwater 3D Scene Reconstruction with Plenoptic Medium Representation
  15. NeurIPS 2025Point Cloud Synthesis Using Inner Product Transforms
  16. NeurIPS 2025Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
  17. NeurIPS 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
  18. NeurIPS 2025Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
  19. NeurIPS 2025PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
  20. NeurIPS 2025PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
  21. NeurIPS 2025PointTruss: K-Truss for Point Cloud Registration
  22. NeurIPS 2025Polyline Path Masked Attention for Vision Transformer
  23. NeurIPS 2025PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations
  24. NeurIPS 2025PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in Endoscopy
  25. NeurIPS 2025Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance
  26. NeurIPS 2025PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching
  27. NeurIPS 2025Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing
  28. NeurIPS 2025ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
  29. NeurIPS 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
  30. NeurIPS 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
  31. NeurIPS 2025RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion
  32. NeurIPS 2025REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints
  33. NeurIPS 2025Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation
  34. NeurIPS 2025ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
  35. NeurIPS 2025Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
  36. NeurIPS 2025Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery
  37. NeurIPS 2025Rectified Point Flow: Generic Point Cloud Pose Estimation
  38. NeurIPS 2025Reframing Gaussian Splatting Densification with Complexity-Density Consistency of Primitives
  39. NeurIPS 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
  40. NeurIPS 2025REOrdering Patches Improves Vision Models
  41. NeurIPS 2025Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
  42. NeurIPS 2025RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
  43. NeurIPS 2025Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction
  44. NeurIPS 2025RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
  45. NeurIPS 2025Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting
  46. NeurIPS 2025ROGR: Relightable 3D Objects using Generative Relighting
  47. NeurIPS 2025SAP: Exact Sorting in Splatting via Screen-Aligned Primitives
  48. NeurIPS 2025SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting
  49. NeurIPS 2025Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
  50. NeurIPS 2025SegMASt3R: Geometry Grounded Segment Matching

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