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 103 / 104 页

  1. NeurIPS 2023Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
  2. NeurIPS 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
  3. NeurIPS 2023LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation
  4. NeurIPS 2023LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation
  5. NeurIPS 2023M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors
  6. NeurIPS 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
  7. NeurIPS 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
  8. NeurIPS 2023Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context
  9. NeurIPS 2023MotionGPT: Human Motion as a Foreign Language
  10. NeurIPS 2023Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
  11. NeurIPS 2023MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
  12. NeurIPS 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
  13. NeurIPS 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
  14. NeurIPS 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
  15. NeurIPS 2023Nearest Neighbour with Bandit Feedback
  16. NeurIPS 2023Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
  17. NeurIPS 2023Neural Image Compression: Generalization, Robustness, and Spectral Biases
  18. NeurIPS 2023NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs
  19. NeurIPS 2023NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation
  20. NeurIPS 2023Norm-guided latent space exploration for text-to-image generation
  21. NeurIPS 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
  22. NeurIPS 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
  23. NeurIPS 2023Optimal Transport-Guided Conditional Score-Based Diffusion Model
  24. NeurIPS 2023Optimizing Prompts for Text-to-Image Generation
  25. NeurIPS 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
  26. NeurIPS 2023PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
  27. NeurIPS 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance
  28. NeurIPS 2023PHOTOSWAP: Personalized Subject Swapping in Images
  29. NeurIPS 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
  30. NeurIPS 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
  31. NeurIPS 2023Point Cloud Completion with Pretrained Text-to-Image Diffusion Models
  32. NeurIPS 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
  33. NeurIPS 2023PromptIR: Prompting for All-in-One Image Restoration
  34. NeurIPS 2023PromptRestorer: A Prompting Image Restoration Method with Degradation Perception
  35. NeurIPS 2023PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
  36. NeurIPS 2023Q-DM: An Efficient Low-bit Quantized Diffusion Model
  37. NeurIPS 2023Quilt-1M: One Million Image-Text Pairs for Histopathology
  38. NeurIPS 2023RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
  39. NeurIPS 2023Real-World Image Variation by Aligning Diffusion Inversion Chain
  40. NeurIPS 2023Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
  41. NeurIPS 2023Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors
  42. NeurIPS 2023Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”
  43. NeurIPS 2023Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”
  44. NeurIPS 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting
  45. NeurIPS 2023Revisiting the Evaluation of Image Synthesis with GANs
  46. NeurIPS 2023Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field
  47. NeurIPS 2023Scalable 3D Captioning with Pretrained Models
  48. NeurIPS 2023SceneScape: Text-Driven Consistent Scene Generation
  49. NeurIPS 2023SEGA: Instructing Text-to-Image Models using Semantic Guidance
  50. NeurIPS 2023Semantic Image Synthesis with Unconditional Generator

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