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 3,224 篇，第 47 / 65 页

  1. ICLR 20243D Reconstruction with Generalizable Neural Fields using Scene Priors
  2. ICLR 20243D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
  3. ICLR 2024ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
  4. ICLR 2024AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
  5. ICLR 2024Approximately Piecewise E(3) Equivariant Point Networks
  6. ICLR 2024Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
  7. ICLR 2024Cameras as Rays: Pose Estimation via Ray Diffusion
  8. ICLR 2024Coordinate-Aware Modulation for Neural Fields
  9. ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
  10. ICLR 2024Data-independent Module-aware Pruning for Hierarchical Vision Transformers
  11. ICLR 2024Decodable and Sample Invariant Continuous Object Encoder
  12. ICLR 2024Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
  13. ICLR 2024DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation
  14. ICLR 2024Denoising Diffusion via Image-Based Rendering
  15. ICLR 2024Differentiable Euler Characteristic Transforms for Shape Classification
  16. ICLR 2024DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model
  17. ICLR 2024DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
  18. ICLR 2024DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  19. ICLR 2024DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
  20. ICLR 2024DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation
  21. ICLR 2024DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
  22. ICLR 2024DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
  23. ICLR 2024ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF
  24. ICLR 2024Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
  25. ICLR 2024EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
  26. ICLR 2024Enhanced Face Recognition using Intra-class Incoherence Constraint
  27. ICLR 2024FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
  28. ICLR 2024Frozen Transformers in Language Models Are Effective Visual Encoder Layers
  29. ICLR 2024Fully Hyperbolic Convolutional Neural Networks for Computer Vision
  30. ICLR 2024Generating Images with 3D Annotations Using Diffusion Models
  31. ICLR 2024Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields
  32. ICLR 2024Ghost on the Shell: An Expressive Representation of General 3D Shapes
  33. ICLR 2024GIM: Learning Generalizable Image Matcher From Internet Videos
  34. ICLR 2024GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
  35. ICLR 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)
  36. ICLR 2024GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
  37. ICLR 2024H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields
  38. ICLR 2024HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
  39. ICLR 2024How to Fine-Tune Vision Models with SGD
  40. ICLR 2024Improving the Convergence of Dynamic NeRFs via Optimal Transport
  41. ICLR 2024Initializing Models with Larger Ones
  42. ICLR 2024InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
  43. ICLR 2024Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
  44. ICLR 2024InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
  45. ICLR 2024Latent 3D Graph Diffusion
  46. ICLR 2024LEAP: Liberate Sparse-View 3D Modeling from Camera Poses
  47. ICLR 2024Learning 3D Particle-based Simulators from RGB-D Videos
  48. ICLR 2024Learning Implicit Representation for Reconstructing Articulated Objects
  49. ICLR 2024Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
  50. ICLR 2024Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

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