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 8 / 17 页

  1. NeurIPS 2025MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
  2. NeurIPS 2025MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
  3. NeurIPS 2025Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
  4. NeurIPS 2025NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
  5. NeurIPS 2025Neural Green’s Functions
  6. NeurIPS 2025NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods
  7. NeurIPS 2025Non-Line-of-Sight 3D Reconstruction with Radar
  8. NeurIPS 2025NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input
  9. NeurIPS 2025Normalize Filters! Classical Wisdom for Deep Vision
  10. NeurIPS 2025Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
  11. NeurIPS 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
  12. NeurIPS 2025Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
  13. NeurIPS 2025ODG: Occupancy Prediction Using Dual Gaussians
  14. NeurIPS 2025Omnidirectional 3D Scene Reconstruction from Single Image
  15. NeurIPS 2025OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation
  16. NeurIPS 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
  17. NeurIPS 2025Online Segment Any 3D Thing as Instance Tracking
  18. NeurIPS 2025OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
  19. NeurIPS 2025OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
  20. NeurIPS 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
  21. NeurIPS 2025Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
  22. NeurIPS 2025Optimized Minimal 3D Gaussian Splatting
  23. NeurIPS 2025Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
  24. NeurIPS 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
  25. NeurIPS 2025PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting
  26. NeurIPS 2025PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors
  27. NeurIPS 2025Plenodium: Underwater 3D Scene Reconstruction with Plenoptic Medium Representation
  28. NeurIPS 2025Point Cloud Synthesis Using Inner Product Transforms
  29. NeurIPS 2025Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
  30. NeurIPS 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
  31. NeurIPS 2025Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
  32. NeurIPS 2025PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
  33. NeurIPS 2025PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
  34. NeurIPS 2025PointTruss: K-Truss for Point Cloud Registration
  35. NeurIPS 2025Polyline Path Masked Attention for Vision Transformer
  36. NeurIPS 2025PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations
  37. NeurIPS 2025PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in Endoscopy
  38. NeurIPS 2025Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance
  39. NeurIPS 2025PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching
  40. NeurIPS 2025Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing
  41. NeurIPS 2025ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
  42. NeurIPS 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
  43. NeurIPS 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
  44. NeurIPS 2025RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion
  45. NeurIPS 2025REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints
  46. NeurIPS 2025Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation
  47. NeurIPS 2025ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
  48. NeurIPS 2025Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
  49. NeurIPS 2025Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery
  50. NeurIPS 2025Rectified Point Flow: Generic Point Cloud Pose Estimation

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