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 25 / 33 页

  1. CVPR 2024Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data
  2. CVPR 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
  3. CVPR 2024Pre-training Vision Models with Mandelbulb Variations
  4. CVPR 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
  5. CVPR 2024Projecting Trackable Thermal Patterns for Dynamic Computer Vision
  6. CVPR 2024PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
  7. CVPR 2024QUADify: Extracting Meshes with Pixel-level Details and Materials from Images
  8. CVPR 2024R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization
  9. CVPR 2024Random Entangled Tokens for Adversarially Robust Vision Transformer
  10. CVPR 2024Real-time 3D-aware Portrait Video Relighting
  11. CVPR 2024ReconFusion: 3D Reconstruction with Diffusion Priors
  12. CVPR 2024Reconstructing Hands in 3D with Transformers
  13. CVPR 2024Reconstruction-free Cascaded Adaptive Compressive Sensing
  14. CVPR 2024RegionGPT: Towards Region Understanding Vision Language Model
  15. CVPR 2024RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method
  16. CVPR 2024RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation
  17. CVPR 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentation
  18. CVPR 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos
  19. CVPR 2024RMT: Retentive Networks Meet Vision Transformers
  20. CVPR 2024RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction
  21. CVPR 2024SANeRF-HQ: Segment Anything for NeRF in High Quality
  22. CVPR 2024SAOR: Single-View Articulated Object Reconstruction
  23. CVPR 2024SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
  24. CVPR 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion
  25. CVPR 2024SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image
  26. CVPR 2024Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
  27. CVPR 2024Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction
  28. CVPR 2024Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
  29. CVPR 2024Sequential Modeling Enables Scalable Learning for Large Vision Models
  30. CVPR 2024SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks
  31. CVPR 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
  32. CVPR 2024SIGNeRF: Scene Integrated Generation for Neural Radiance Fields
  33. CVPR 2024Single View Refractive Index Tomography with Neural Fields
  34. CVPR 2024Single-View Scene Point Cloud Human Grasp Generation
  35. CVPR 2024Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction
  36. CVPR 2024SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers
  37. CVPR 2024SNI-SLAM: Semantic Neural Implicit SLAM
  38. CVPR 2024SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields
  39. CVPR 2024SODA: Bottleneck Diffusion Models for Representation Learning
  40. CVPR 2024Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers
  41. CVPR 2024Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
  42. CVPR 2024Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo
  43. CVPR 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction
  44. CVPR 2024Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation
  45. CVPR 2024SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream
  46. CVPR 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks
  47. CVPR 2024SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM
  48. CVPR 2024Splatter Image: Ultra-Fast Single-View 3D Reconstruction
  49. CVPR 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
  50. CVPR 2024SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation

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