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 1,371 篇，第 12 / 28 页

  1. NeurIPS 2025DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
  2. NeurIPS 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
  3. NeurIPS 2025Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
  4. NeurIPS 2025DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
  5. NeurIPS 2025DreamLight: Towards Harmonious and Consistent Image Relighting
  6. NeurIPS 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
  7. NeurIPS 2025DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models
  8. NeurIPS 2025EchoShot: Multi-Shot Portrait Video Generation
  9. NeurIPS 2025EditInfinity: Image Editing with Binary-Quantized Generative Models
  10. NeurIPS 2025EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting
  11. NeurIPS 2025Efficient Part-level 3D Object Generation via Dual Volume Packing
  12. NeurIPS 2025Efficient RAW Image Deblurring with Adaptive Frequency Modulation
  13. NeurIPS 2025Efficient Rectified Flow for Image Fusion
  14. NeurIPS 2025Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
  15. NeurIPS 2025End-to-End Vision Tokenizer Tuning
  16. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
  17. NeurIPS 2025Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
  18. NeurIPS 2025Entropy Rectifying Guidance for Diffusion and Flow Models
  19. NeurIPS 2025EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
  20. NeurIPS 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
  21. NeurIPS 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inference
  22. NeurIPS 2025Exploring Diffusion Transformer Designs via Grafting
  23. NeurIPS 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
  24. NeurIPS 2025Fast constrained sampling in pre-trained diffusion models
  25. NeurIPS 2025Fast Data Attribution for Text-to-Image Models
  26. NeurIPS 2025Feedback Guidance of Diffusion Models
  27. NeurIPS 2025FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies
  28. NeurIPS 2025FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
  29. NeurIPS 2025FIPER: Factorized Features for Robust Image Super-Resolution and Compression
  30. NeurIPS 2025FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
  31. NeurIPS 2025FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
  32. NeurIPS 2025Flexible MOF Generation with Torsion-Aware Flow Matching
  33. NeurIPS 2025FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
  34. NeurIPS 2025Flow-GRPO: Training Flow Matching Models via Online RL
  35. NeurIPS 2025FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
  36. NeurIPS 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
  37. NeurIPS 2025ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
  38. NeurIPS 2025Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge
  39. NeurIPS 2025Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation
  40. NeurIPS 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
  41. NeurIPS 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
  42. NeurIPS 2025FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
  43. NeurIPS 2025FRN: Fractal-Based Recursive Spectral Reconstruction Network
  44. NeurIPS 2025From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
  45. NeurIPS 2025FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
  46. NeurIPS 2025FuncGenFoil: Airfoil Generation and Editing Model in Function Space
  47. NeurIPS 2025Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
  48. NeurIPS 2025GauSAM: Contour‑Guided 2D Gaussian Fields for Multi‑Scale Medical Image Segmentation with Segment Anything
  49. NeurIPS 2025Generating and Checking DNN Verification Proofs
  50. NeurIPS 2025Generating Physically Sound Designs from Text and a Set of Physical Constraints

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