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 1,639 篇，第 11 / 33 页

  1. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
  2. CVPR 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
  3. CVPR 2025AffordDP: Generalizable Diffusion Policy with Transferable Affordance
  4. CVPR 2025An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
  5. CVPR 2025AniGrad: Anisotropic Gradient-Adaptive Sampling for 3D Reconstruction From Monocular Video
  6. CVPR 2025AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
  7. CVPR 2025AnyMap: Learning a General Camera Model for Structure-from-Motion with Unknown Distortion in Dynamic Scenes
  8. CVPR 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
  9. CVPR 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
  10. CVPR 2025ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points
  11. CVPR 2025Argus: A Compact and Versatile Foundation Model for Vision
  12. CVPR 2025ARM: Appearance Reconstruction Model for Relightable 3D Generation
  13. CVPR 2025ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting
  14. CVPR 2025Associative Transformer
  15. CVPR 2025ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
  16. CVPR 2025AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting
  17. CVPR 2025AutoURDF: Unsupervised Robot Modeling from Point Cloud Frames Using Cluster Registration
  18. CVPR 2025BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting
  19. CVPR 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
  20. CVPR 2025BG-Triangle: Bezier Gaussian Triangle for 3D Vectorization and Rendering
  21. CVPR 2025BHViT: Binarized Hybrid Vision Transformer
  22. CVPR 2025BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
  23. CVPR 2025BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
  24. CVPR 2025BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing
  25. CVPR 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior
  26. CVPR 2025Building Vision Models upon Heat Conduction
  27. CVPR 2025BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer
  28. CVPR 2025CamPoint: Boosting Point Cloud Segmentation with Virtual Camera
  29. CVPR 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image
  30. CVPR 2025CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
  31. CVPR 2025Chain of Semantics Programming in 3D Gaussian Splatting Representation for 3D Vision Grounding
  32. CVPR 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework
  33. CVPR 2025CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
  34. CVPR 2025Coherent 3D Portrait Video Reconstruction via Triplane Fusion
  35. CVPR 2025ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration
  36. CVPR 2025CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
  37. CVPR 2025CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
  38. CVPR 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
  39. CVPR 2025Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph
  40. CVPR 2025Continuous 3D Perception Model with Persistent State
  41. CVPR 2025Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting
  42. CVPR 2025Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion
  43. CVPR 2025CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
  44. CVPR 2025CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
  45. CVPR 2025D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.
  46. CVPR 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
  47. CVPR 2025DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
  48. CVPR 2025DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge
  49. CVPR 2025DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis
  50. CVPR 2025Deformable Radial Kernel Splatting

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