Image Generation

Ask about this topic

Overview

Image generation studies how to produce realistic, useful images from inputs such as text prompts, reference pictures, sketches, spatial layouts, or scientific measurements. Common approaches include diffusion and flow-matching models that refine images step by step, autoregressive models that generate visual tokens in sequence, and GANs used in some specialized settings. Researchers improve control and efficiency with techniques such as reference conditioning, geometric constraints, preference optimization, and iterative agent feedback, and evaluate results on benchmarks such as ImageNet, COCO, and GenEval as well as domain-specific tasks. A central challenge is balancing visual quality, prompt accuracy, identity and structural consistency, diversity, and generation cost; realistic appearance alone does not guarantee that an image is correct or safe.

Latest papers

CardsList

474 papers63 papers in the last four weeks, up 75% on the four weeks before. 0.4% of all new papers.

  1. Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation

    Apr 24, 2026Ran Zhao, Sheng Jin, Size Wu +5T2I GenerationImage Generation

    Huazhong University of Science and Technology · The University of Hong Kong · S-Lab, Nanyang Technological University

  2. UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

    Apr 23, 2026Yanran Zhang, Wenzhao Zheng, Yifei Li +5Image GenerationAI-Generated Image Detection

    Department of Automation, Tsinghua University, China

  3. Linear Image Generation by Synthesizing Exposure Brackets

    Apr 22, 2026Yuekun Dai, Zhoutong Zhang, Shangchen Zhou +1T2I GenerationImage Generation

    S-Lab, Nanyang Technological University · Adobe NextCam · Adobe Research

  4. Image Generators are Generalist Vision Learners

    Apr 22, 2026Valentin Gabeur, Shangbang Long, Songyou Peng +22Image SegmentationVisual Representation Learning

    ★project leads and equal contributions · ∇core contributors · †project advisors +1

  5. CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation

    Apr 21, 2026Nassim Sadallah, Mohand Saïd AlliliSynthetic Data AugmentationImage Generation

    LARIVIA Lab, Department of Computer Science and Engineering · Gatineau, QC, Canada

  6. Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance

    Apr 21, 2026Weitao DuFlow MatchingImage Generation

    DAMO Academy

  7. MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures

    Apr 19, 2026Vasileios Toulatzis, Sofia Theodoridou, Ioannis FudosImage GenerationImage Restoration

    University of Ioannina, Greece

  8. SciDraw-6K: A Multilingual Scientific Illustration Dataset Generated by Google Gemini

    Apr 19, 2026Davie ChenScientific VisualizationSynthetic Data Generation

    University of Arts in Pozna´n

  9. Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation

    Apr 18, 2026Minyan Luo, Yuxin Zhang, Yifei Li +5Image GenerationCompositional Image Generation

    MAIS,Institute of Automation, Chinese Academy of Sciences · ByteDance · Tsinghua University +4

  10. Frequency-Aware Flow Matching for High-Quality Image Generation

    Apr 16, 2026Sucheng Ren, Qihang Yu, Ju He +3Flow MatchingConditional Image Generation

    Johns Hopkins University · ByteDance

  11. LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

    Apr 16, 2026Zhanhao Liang, Tao Yang, Jie Wu +2Diffusion Model AlignmentFlow Matching

    1The Australian National University · 2ByteDance Seed

  12. Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation

    Apr 16, 2026Chisato Kumada, Satoru Hiwa, Tomoyuki HiroyasuImage GenerationDiffusion Models

    Graduate School of Life and Medical Sciences · Doshisha University · Kyoto, Japan +1

  13. Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation

    Apr 15, 2026Zoe De Simone, Angie Boggust, Fredo Durand +2T2I GenerationImage Generation

    MIT CSAIL, Cambridge, MA, USA

  14. ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding

    Apr 15, 2026Tianze Xia, Zijian Ning, Zonglin Zhao +1Multi-Subject Image GenerationImage Generation

    Huazhong University of Science and Technology

  15. StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation

    Apr 14, 2026Yinxi He, Kang Liao, Chunyu Lin +2Image GenerationDiffusion-Based Image Generation

    Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China, and also with Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing 100044, China. · College of Computing and Data Science, Nanyang Technological University, Singapore.

  16. Continuous Adversarial Flow Models

    Apr 13, 2026Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2Flow-Based Generative ModelingImage Generation

    ByteDance Seed

  17. HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation

    Apr 13, 2026Yongxiang Liu, Jie Zhou, Yafei Song +2Image GenerationRemote Sensing

    College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha 410073, China.

  18. ReContraster: Making Your Posters Stand Out with Regional Contrast

    Apr 12, 2026Peixuan Zhang, Zijian Jia, Ziqi Cai +3Image GenerationCompositional Image Generation

    School of Artificial Intelligence, Beijing University of Posts and Telecommunications · State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University · National Engineering Research Center of Visual Technology, School of Computer Science, Peking University +1

  19. Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation

    Apr 10, 2026Huiang He, Shengchu Zhao, Jianwen Huang +7Multi-View Image Synthesis3D Texture Generation

    Math Magic · South China University of Technology

  20. Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models

    Apr 10, 2026Wongi Jeong, Hoigi Seo, Se Young ChunImage GenerationDiffusion Model Acceleration

    Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea · INMC & IPAI, Seoul National University, Republic of Korea

  21. Lookahead Drifting Model

    Apr 10, 2026Guoqiang Zhang, Kenta Niwa, W. Bastiaan KleijnDrifting ModelsImage Generation

    University of Exeter · NTT Communication Science Laboratories · Victoria University of Wellington

  22. MixFlow: Mixed Source Distributions Improve Rectified Flows

    Apr 10, 2026Nazir Nayal, Christopher Wewer, Jan Eric LenssenRectified FlowImage Generation

    Max Planck Institute for Informatics, Saarland Informatics Campus, Germany

  23. ELT: Elastic Looped Transformers for Visual Generation

    Apr 10, 2026Sahil Goyal, Swayam Agrawal, Gautham Govind Anil +3Image GenerationTransformer

  24. CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation

    Apr 10, 2026Sanyam Jain, Pragya Kandari, Manit Singhal +2Image EditingCompositional Image Generation

    Adobe

  25. Guiding a Diffusion Model by Swapping Its Tokens

    Apr 9, 2026Weijia Zhang, Yuehao Liu, Shanyan Guan +4Diffusion Model GuidanceDiffusion Guidance

    MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University · vivo Mobile Communication Co., Ltd.

  26. Multimodal Large Language Models for Multi-Subject In-Context Image Generation

    Apr 8, 2026Yucheng Zhou, Dubing Chen, Huan Zheng +1Multi-Subject Image GenerationImage Generation

    SKL-IOTSC, CIS, University of Macau

  27. VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis

    Apr 8, 2026Jian Yu, Fei Shen, Cong Wang +4Image GenerationControllable Image Generation

    Nanjing University of Science and Technology · National University of Singapore · Nanjing University +1

  28. FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

    Apr 8, 2026Junchao Yi, Rui Zhao, Jiahao Tang +7Multimodal GenerationImage Generation

    University of Electronic Science and Technology of China · National University of Singapore · Central South University +2

  29. ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment

    Apr 8, 2026Zhipeng Bian, Jieming Zhu, Qijiong Liu +6Image GenerationDiffusion-Based Image Generation

    Huazhong University of Science and Technology · Huawei Noah’s Ark Lab · Hong Kong Polytechnic University +1

  30. ODE-free Neural Flow Matching for One-Step Generative Modeling

    Apr 7, 2026Xiao ShouOne-Step Generative ModelingFlow Matching

    Baylor University