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 5 / 17 页

  1. NeurIPS 2026Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
  2. NeurIPS 2026Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
  3. NeurIPS 2026Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
  4. NeurIPS 2026Visual-to-Executable Procedural Reconstruction of Buildings.
  5. NeurIPS 2026ViT-AdaLA: Adapting Vision Transformers with Linear Attention
  6. NeurIPS 2026VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph
  7. NeurIPS 2026VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
  8. NeurIPS 2026Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding
  9. NeurIPS 2026Walking Through 3D Spaces: Spatial Routing for Referring 3D Gaussian Splatting Segmentation
  10. NeurIPS 2026WavNAF: Learning Wave Propagation Priors for Neural Acoustic Fields
  11. NeurIPS 2026When and How to Canonize: a Generalization Perspective
  12. NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
  13. NeurIPS 20253D Equivariant Visuomotor Policy Learning via Spherical Projection
  14. NeurIPS 20253D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
  15. NeurIPS 20253D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion
  16. NeurIPS 20253D Visual Illusion Depth Estimation
  17. NeurIPS 20253D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
  18. NeurIPS 20253DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
  19. NeurIPS 20253EED: Ground Everything Everywhere in 3D
  20. NeurIPS 20254D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
  21. NeurIPS 20254D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
  22. NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
  23. NeurIPS 2025Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
  24. NeurIPS 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
  25. NeurIPS 2025AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
  26. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
  27. NeurIPS 2025Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression
  28. NeurIPS 2025Anti-Aliased 2D Gaussian Splatting
  29. NeurIPS 2025APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
  30. NeurIPS 2025Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
  31. NeurIPS 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
  32. NeurIPS 2025AutoPartGen: Autoregressive 3D Part Generation and Discovery
  33. NeurIPS 2025BEDLAM2.0: Synthetic humans and cameras in motion
  34. NeurIPS 2025Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
  35. NeurIPS 2025BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation
  36. NeurIPS 2025Bézier Splatting for Fast and Differentiable Vector Graphics Rendering
  37. NeurIPS 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
  38. NeurIPS 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
  39. NeurIPS 2025Building 3D Representations and Generating Motions From a Single Image via Video-Generation
  40. NeurIPS 2025CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
  41. NeurIPS 2025CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
  42. NeurIPS 2025Cameras as Relative Positional Encoding
  43. NeurIPS 2025Can NeRFs "See" without Cameras?
  44. NeurIPS 2025Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment
  45. NeurIPS 2025CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
  46. NeurIPS 2025ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
  47. NeurIPS 2025CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering
  48. NeurIPS 2025CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
  49. NeurIPS 2025Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
  50. NeurIPS 2025Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm

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