图像生成论文趋势 2023–2026

文生图与图像合成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,184 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

图像生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202317011874418780
20243181991565431,216
20254302781476121,467
20264533492306891,721

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

全部图像生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 5,184 篇，第 88 / 104 页

  1. NeurIPS 2024Soft Superpixel Neighborhood Attention
  2. NeurIPS 2024Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras
  3. NeurIPS 2024SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
  4. NeurIPS 2024Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
  5. NeurIPS 2024Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
  6. NeurIPS 2024STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics
  7. NeurIPS 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
  8. NeurIPS 2024Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
  9. NeurIPS 2024Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
  10. NeurIPS 2024SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition
  11. NeurIPS 2024Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
  12. NeurIPS 2024Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
  13. NeurIPS 2024T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
  14. NeurIPS 2024T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
  15. NeurIPS 2024Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
  16. NeurIPS 2024Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
  17. NeurIPS 2024Taming Generative Diffusion Prior for Universal Blind Image Restoration
  18. NeurIPS 2024Task Me Anything
  19. NeurIPS 2024Test-Time Dynamic Image Fusion
  20. NeurIPS 2024Tetrahedron Splatting for 3D Generation
  21. NeurIPS 2024Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model
  22. NeurIPS 2024TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
  23. NeurIPS 2024Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
  24. NeurIPS 2024TFG: Unified Training-Free Guidance for Diffusion Models
  25. NeurIPS 2024TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
  26. NeurIPS 2024Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
  27. NeurIPS 2024TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
  28. NeurIPS 2024Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
  29. NeurIPS 2024Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
  30. NeurIPS 2024Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
  31. NeurIPS 2024Towards Visual Text Design Transfer Across Languages
  32. NeurIPS 2024TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
  33. NeurIPS 2024Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
  34. NeurIPS 2024U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
  35. NeurIPS 2024UDON: Universal Dynamic Online distillatioN for generic image representations
  36. NeurIPS 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
  37. NeurIPS 2024UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
  38. NeurIPS 2024Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
  39. NeurIPS 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
  40. NeurIPS 2024UNIT: Unifying Image and Text Recognition in One Vision Encoder
  41. NeurIPS 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
  42. NeurIPS 2024Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
  43. NeurIPS 2024Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
  44. NeurIPS 2024UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
  45. NeurIPS 2024Variational Flow Matching for Graph Generation
  46. NeurIPS 2024Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
  47. NeurIPS 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
  48. NeurIPS 2024Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
  49. NeurIPS 2024What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
  50. NeurIPS 2024Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)

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 查图像生成在 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": "image-generation"}

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图像生成论文？
共 5,184 篇，按年份分别是 2023 年 780 篇、2024 年 1,216 篇、2025 年 1,467 篇、2026 年 1,721 篇。
NeurIPS 2026 有多少篇图像生成论文？
NeurIPS 2026 有 453 篇图像生成论文，上一届是 430 篇。
ICLR 2026 有多少篇图像生成论文？
ICLR 2026 有 349 篇图像生成论文，上一届是 278 篇。
ICML 2026 有多少篇图像生成论文？
ICML 2026 有 230 篇图像生成论文，上一届是 147 篇。
CVPR 2026 有多少篇图像生成论文？
CVPR 2026 有 689 篇图像生成论文，上一届是 612 篇。
哪个会议的图像生成论文最多？
CVPR，2023–2026 年共 2,262 篇。

「计算机视觉」下的其他主题