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 40 / 104 页

  1. CVPR 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
  2. CVPR 2025GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration
  3. CVPR 2025Generalized Zero-Shot Classification via Semantics-Free Inter-Class Feature Generation
  4. CVPR 2025Generative Gaussian Splatting for Unbounded 3D City Generation
  5. CVPR 2025Generative Image Layer Decomposition with Visual Effects
  6. CVPR 2025Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
  7. CVPR 2025Generative Zero-Shot Composed Image Retrieval
  8. CVPR 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videos
  9. CVPR 2025GenVDM: Generating Vector Displacement Maps From a Single Image
  10. CVPR 2025Geometry in Style: 3D Stylization via Surface Normal Deformation
  11. CVPR 2025Glossy Object Reconstruction with Cost-effective Polarized Acquisition
  12. CVPR 2025Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion
  13. CVPR 2025GPS as a Control Signal for Image Generation
  14. CVPR 2025GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs
  15. CVPR 2025GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning
  16. CVPR 2025GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking
  17. CVPR 2025Gyro-based Neural Single Image Deblurring
  18. CVPR 2025Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
  19. CVPR 2025Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
  20. CVPR 2025Hash3D: Training-free Acceleration for 3D Generation
  21. CVPR 2025HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator
  22. CVPR 2025Hierarchical Adaptive Filtering Network for Text Image Specular Highlight Removal
  23. CVPR 2025Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation
  24. CVPR 2025HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion
  25. CVPR 2025High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
  26. CVPR 2025HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
  27. CVPR 2025HistoFS: Non-IID Histopathologic Whole Slide Image Classification via Federated Style Transfer with RoI-Preserving
  28. CVPR 2025HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
  29. CVPR 2025Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification
  30. CVPR 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
  31. CVPR 2025HUNet: Homotopy Unfolding Network for Image Compressive Sensing
  32. CVPR 2025HVI: A New Color Space for Low-light Image Enhancement
  33. CVPR 2025Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
  34. CVPR 2025Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
  35. CVPR 2025HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
  36. CVPR 2025HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories
  37. CVPR 2025I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models
  38. CVPR 2025ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models
  39. CVPR 2025ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
  40. CVPR 2025Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
  41. CVPR 2025Identity-preserving Distillation Sampling by Fixed-Point Iterator
  42. CVPR 2025Identity-Preserving Text-to-Video Generation by Frequency Decomposition
  43. CVPR 2025IDOL: Instant Photorealistic 3D Human Creation from a Single Image
  44. CVPR 2025IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
  45. CVPR 2025ILIAS: Instance-Level Image retrieval At Scale
  46. CVPR 2025Illumination Spectrum Estimation for Multispectral Images via Surface Reflectance Modeling and Spatial-Spectral Feature Generation
  47. CVPR 2025IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner
  48. CVPR 2025Image Generation Diversity Issues and How to Tame Them
  49. CVPR 2025Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation
  50. CVPR 2025Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

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