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 1,721 篇，第 32 / 35 页

  1. NeurIPS 2026OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
  2. NeurIPS 2026P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
  3. NeurIPS 2026PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes
  4. NeurIPS 2026Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
  5. NeurIPS 2026Parameterized Stripe Attention for Efficient Video Generation
  6. NeurIPS 2026Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation
  7. NeurIPS 2026ParaPC-FM: Accelerating Parallel Sampling via Principled Initialization
  8. NeurIPS 2026PARE: Pruning and Adaptive Routing for Efficient Video Generation
  9. NeurIPS 2026PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion
  10. NeurIPS 2026Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
  11. NeurIPS 2026PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
  12. NeurIPS 2026Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation
  13. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
  14. NeurIPS 2026PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation
  15. NeurIPS 2026PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
  16. NeurIPS 2026PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
  17. NeurIPS 2026PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
  18. NeurIPS 2026Polar Transformers: $SO(2)^K$-Equivariant Angular Attention for Cryo-EM Image-Set Processing
  19. NeurIPS 2026PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery
  20. NeurIPS 2026Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation
  21. NeurIPS 2026Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
  22. NeurIPS 2026Primal-Dual Flow Matching for Sample-Wise Constrained Generation
  23. NeurIPS 2026PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
  24. NeurIPS 2026PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
  25. NeurIPS 2026Probability-Conserving Flow Guidance
  26. NeurIPS 2026Probing Visual Planning in Image Editing Models
  27. NeurIPS 2026ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images
  28. NeurIPS 2026Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation
  29. NeurIPS 2026Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
  30. NeurIPS 2026Pygmalion: Bridging Reconstruction and Generation in Sparse Voxel-based 3D Modeling
  31. NeurIPS 2026Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
  32. NeurIPS 2026QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
  33. NeurIPS 2026RADAR: Relative Angular Divergence Across Representations
  34. NeurIPS 2026RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
  35. NeurIPS 2026RADIUM: RadioActive Decay of Image-Underlaid Marks
  36. NeurIPS 2026Random-Projection Tree Stein Variational Gradient Descent
  37. NeurIPS 2026RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
  38. NeurIPS 2026RANSAC Scoring Done Right
  39. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
  40. NeurIPS 2026RB-LDC: Redundancy-Balanced Latent Coding for Robust Diffusion
  41. NeurIPS 2026Re-evaluating Confidence Remasking in Masked Diffusion Language Models
  42. NeurIPS 2026Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
  43. NeurIPS 2026Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning
  44. NeurIPS 2026Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
  45. NeurIPS 2026RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
  46. NeurIPS 2026RefineTok: Scale-Wise Tokenization for Progressive Visual Refinement
  47. NeurIPS 2026ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections
  48. NeurIPS 2026REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
  49. NeurIPS 2026ReGuidance: Diffusion Steering with Strong Latent Initializations Solves Hard Inverse Problems
  50. NeurIPS 2026Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images

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