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 563 篇，第 8 / 12 页

  1. ICLR 2023GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis
  2. ICLR 2023General Neural Gauge Fields
  3. ICLR 2023GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
  4. ICLR 2023Grounding Graph Network Simulators using Physical Sensor Observations
  5. ICLR 2023Human MotionFormer: Transferring Human Motions with Vision Transformers
  6. ICLR 2023Interpretable Geometric Deep Learning via Learnable Randomness Injection
  7. ICLR 2023Is Attention All That NeRF Needs?
  8. ICLR 2023ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
  9. ICLR 2023Learning to Estimate Shapley Values with Vision Transformers
  10. ICLR 2023Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models
  11. ICLR 2023LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
  12. ICLR 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
  13. ICLR 2023Masked Vision and Language Modeling for Multi-modal Representation Learning
  14. ICLR 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
  15. ICLR 2023MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
  16. ICLR 2023MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
  17. ICLR 2023Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN
  18. ICLR 2023Monocular Scene Reconstruction with 3D SDF Transformers
  19. ICLR 2023NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes
  20. ICLR 2023Neural Groundplans: Persistent Neural Scene Representations from a Single Image
  21. ICLR 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling
  22. ICLR 2023Novel View Synthesis with Diffusion Models
  23. ICLR 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
  24. ICLR 2023Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
  25. ICLR 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
  26. ICLR 2023QuAnt: Quantum Annealing with Learnt Couplings
  27. ICLR 2023Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation
  28. ICLR 2023S-NeRF: Neural Radiance Fields for Street Views
  29. ICLR 2023Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
  30. ICLR 2023Sparse Token Transformer with Attention Back Tracking
  31. ICLR 2023SQA3D: Situated Question Answering in 3D Scenes
  32. ICLR 2023Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields
  33. ICLR 2023Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
  34. ICLR 2023UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
  35. ICLR 2023View Synthesis with Sculpted Neural Points
  36. ICLR 2023Vision Transformer Adapter for Dense Predictions
  37. ICLR 2023Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
  38. ICLR 2023Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
  39. ICLR 2023WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations
  40. ICML 2023A Closer Look at Self-Supervised Lightweight Vision Transformers
  41. ICML 2023A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
  42. ICML 2023Can Forward Gradient Match Backpropagation?
  43. ICML 2023Efficient Graph Field Integrators Meet Point Clouds
  44. ICML 2023Equivariance with Learned Canonicalization Functions
  45. ICML 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency
  46. ICML 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
  47. ICML 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
  48. ICML 2023Linear optimal partial transport embedding
  49. ICML 2023MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses
  50. ICML 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

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