图像生成

Synthetic Melanoma Image Generation and Evaluation Using Generative Adversarial Networks

利用生成对抗网络合成黑色素瘤图像及其评估

Pei-Yu Lin, Yidan Shen, Neville Mathew, Renjie Hu, Siyu Huang, Courtney M. Queen, Cameron E. West, Ana Ciurea, George Zouridakis

机构 * Department of Engineering Technology, University of Houston（休斯顿大学工程技术系） ； Department of Electrical and Computer Engineering, University of Houston（休斯顿大学电气与计算机工程系） ； Department of Information Science Technology, University of Houston（休斯顿大学信息科学与技术系） ； School of Computing, Clemson University（克莱姆斯大学计算学院） ； Department of Public Health, Texas Tech University（德克萨斯技术大学公共卫生系） ； Department of Dermatology and Pathology, Texas Tech University（德克萨斯技术大学皮肤科与病理学系） ； Department of Dermatology, University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心皮肤科） ； Department of Biomedical Engineering, University of Houston（休斯顿大学生物医学工程系） 纠错

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

AI总结 本文通过比较四种GAN架构，生成高分辨率黑色素瘤图像，发现StyleGAN2在定量性能和感知质量上表现最佳，且能有效缓解黑色素瘤数据集中的类别不平衡问题。

Comments 18 pages, 7 figures. already accepted to MDPI bioengineering

Journal ref Bioengineering 2026, 13, 245

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

事实性至关重要：当图像生成与编辑遇见结构化视觉

Le Zhuo, Songhao Han, Yuandong Pu, Boxiang Qiu, Sayak Paul, Yue Liao, Yihao Liu, Jie Shao, Xi Chen, Si Liu, Hongsheng Li

机构 * CUHK MMLab（香港大学多模态实验室） ； Beihang University（北京航空航天大学） ； Krea AI（Krea人工智能） ； Shanghai Jiao Tong University（上海交通大学） ； Shanghai AI Lab（上海人工智能实验室） ； Hugging Face ； National University of Singapore（新加坡国立大学） ； ByteDance（字节跳动） ； The University of Hong Kong（香港大学） 纠错

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

AI总结 本文提出了一种统一模型，通过整合视觉语言模型和FLUX.1 Kontext，提升结构化视觉生成与编辑的多模态理解与事实准确性。

Comments Accepted by ICLR 2026, Project page: https://structvisuals.github.io

Autoregressive Image Generation with Randomized Parallel Decoding

具有随机并行解码的自回归图像生成

Haopeng Li, Jinyue Yang, Guoqi Li, Huan Wang

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

AI总结 ARPG通过解耦的位置指导与内容表示，实现高效的随机顺序图像生成，提升推理速度和零样本泛化能力。

Comments The Fourteenth International Conference on Learning Representations (ICLR 2026)

SCU-CGAN: Enhancing Fire Detection through Synthetic Fire Image Generation and Dataset Augmentation

SCU-CGAN：通过合成火灾图像生成和数据集增强提升火灾检测

Ju-Young Kim, Ji-Hong Park, Gun-Woo Kim

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

AI总结 SCU-CGAN通过合成火灾图像生成和数据集增强提升火灾检测性能，显著提高检测模型的准确性。

Comments Accepted for main track at MobieSec 2024 (not published in the proceedings)

SinSEMI: A One-Shot Image Generation Model and Data-Efficient Evaluation Framework for Semiconductor Inspection Equipment

ChunLiang Wu, Xiaochun Li

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

The Describe-Then-Generate Bottleneck: How VLM Descriptions Alter Image Generation Outcomes

Sai Varun Kodathala, Rakesh Vunnam

机构 * Sports Vision, Inc.（体育视觉公司） ； Vizworld, Inc.（Vizworld公司） 纠错

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments 13 pages, 7 Figures

Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models

Oliver Grainge, Sania Waheed, Jack Stilgoe, Michael Milford, Shoaib Ehsan

专题命中 图像生成评测 ：generative vision(title)；分类 cs.CV

Comments Accepted to AAAI Fall Symposium 2025 on AI Trustworthiness and Risk Assessment for Challenging Contexts (ATRACC)

SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning

Zhewei Dai, Shilei Zeng, Haotian Liu, Xurui Li, Feng Xue, Yu Zhou

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院） ； Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology（华中科技大学智能互联网技术重点实验室） ； Artificial Intelligence Research Institute, Wuhan JingCe Electronic Group Co.,LTD（武汉捷成电子集团有限公司人工智能研究所） ； Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系） 纠错

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments Accepted at ICCV2025

Metrics that matter: Evaluating image quality metrics for medical image generation

Yash Deo, Yan Jia, Toni Lassila, William A. P. Smith, Tom Lawton, Siyuan Kang, Alejandro F. Frangi, Ibrahim Habli

机构 * Department of Computer Science, University of York（约克大学计算机科学系） ； School of Computer Science, University of Leeds（利兹大学计算机科学学院） ； Department of Computing and Mathematics, Manchester Metropolitan University（曼彻斯特 Metropolitan 大学计算与数学系） ； Department of Computer Science, School of Engineering, University of Manchester（曼彻斯特大学计算机科学系） ； School of Health Sciences, Division of Informatics, Imaging and Data Sciences, University of Manchester（曼彻斯特大学健康科学学院） ； Department of Cardiovascular Sciences, KU Leuven（布鲁塞尔自由大学心血管科学系） ； Department of Electrical Engineering (ESAT), KU Leuven（布鲁塞尔自由大学电子工程系） ； Improvement Academy, Bradford Institute for Health Research, Bradford Royal Infirmary（改进学院，布拉德福德健康研究中心，布拉德福德皇家医院） 纠错

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Wavelet-based Variational Autoencoders for High-Resolution Image Generation

Andrew Kiruluta

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Towards Generalization of Tactile Image Generation: Reference-Free Evaluation in a Leakage-Free Setting

Cagri Gungor, Derek Eppinger, Adriana Kovashka

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Assessing Robustness via Score-Based Adversarial Image Generation

Marcel Kollovieh, Lukas Gosch, Marten Lienen, Yan Scholten, Leo Schwinn, Stephan Günnemann

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

Lokesh Veeramacheneni, Moritz Wolter, Hildegard Kuehne, Juergen Gall

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

BF-GAN: Development of an AI-driven Bubbly Flow Image Generation Model Using Generative Adversarial Networks

Wen Zhou, Shuichiro Miwa, Yang Liu, Koji Okamoto

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Enhancing Early Diabetic Retinopathy Detection through Synthetic DR1 Image Generation: A StyleGAN3 Approach

Sagarnil Das, Pradeep Walia

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments 13 pages, 11 figures

Normalizing Flow-Based Metric for Image Generation

Pranav Jeevan, Neeraj Nixon, Amit Sethi

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments 15 pages, 16 figures

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

Zanlin Ni, Yulin Wang, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments Accepted by ECCV2024

Measuring Diversity in Co-creative Image Generation

Francisco Ibarrola, Kazjon Grace

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization

Kshama Kodthalu Shivashankara, Deepanshi, Afagh Mehri Shervedani, Gari D. Clifford, Matthew A. Reyna, Reza Sameni

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Staging E-Commerce Products for Online Advertising using Retrieval Assisted Image Generation

Yueh-Ning Ku, Mikhail Kuznetsov, Shaunak Mishra, Paloma de Juan

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments Accepted for publication in AdKDD 2023

Renderers are Good Zero-Shot Representation Learners: Exploring Diffusion Latents for Metric Learning

Michael Tang, David Shustin

专题命中 图像生成评测 ：diffusion(title)；分类 cs.CV

Adaptive Feature Interpolation for Low-Shot Image Generation

Mengyu Dai, Haibin Hang, Xiaoyang Guo

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

Comments ECCV'22. Code available at https://github.com/dzld00/Adaptive-Feature-Interpolation-for-Low-Shot-Image-Generation

Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluation

August DuMont Schütte, Jürgen Hetzel, Sergios Gatidis, Tobias Hepp, Benedikt Dietz, Stefan Bauer, Patrick Schwab

专题命中 图像生成评测 ：image generation(title)；分类 cs.CV

TIGEr: Text-to-Image Grounding for Image Caption Evaluation

Ming Jiang, Qiuyuan Huang, Lei Zhang, Xin Wang, Pengchuan Zhang, Zhe Gan, Jana Diesner, Jianfeng Gao

专题命中 图像生成评测 ：text-to-image(title)；分类 cs.CV

ReVision : A Post-Hoc, Vision-Based Technique for Replacing Unacceptable Concepts in Image Generation Pipeline

ReVision：一种基于视觉的后处理技术，用于在图像生成管道中替换不可接受的概念

Gurjot Singh, Prabhjot Singh, Aashima Sharma, Maninder Singh, Ryan Ko

专题命中 图像生成评测 ：image generation(title)

AI总结 ReVision是一种无需训练的后处理框架，通过视觉模型检测并替换图像生成中不安全的概念，提升安全性与生成质量。

Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization

基于扩散Transformer的生成式检索：度量有序序列训练与混合策略偏好优化

Chenghao Liu, Yu Zhang, Zhongtao Jiang, Kun Xu, Zhenwei An, Renzhi Wang, Zhao Wang, Jiachen Zhang, Yuxiao Zhang, Kun Xu, Songfang Huang

机构 * Peking University（北京大学） 纠错

专题命中 图像生成评测 ：diffusion(title)

AI总结 针对模式保持的属性检索任务，提出MO-DiT+HPPO框架，通过度量有序训练和混合策略偏好优化，在八个领域分割中七个取得显著提升。

Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles

评估作为进化：将对抗扩散转化为自动驾驶的闭环课程

Yicheng Guo, Jiaqi Liu, Chengkai Xu, Peng Hang, Jian Sun

机构 * College of Transportation, Tongji University（同济大学交通运输学院） ； Department of Computer Science, University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校计算机科学系） 纠错

专题命中 图像生成评测 ：diffusion(title)

AI总结 本文提出E²框架，通过闭环方法将对抗生成转化为自动驾驶的闭环课程，提升系统鲁棒性。

Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization

Hiroaki Chiba-Okabe, Weijie J. Su

专题命中 图像生成评测 ：image generation(title)

Comments 23 pages, 10 figures

Journal ref Sci Rep 15, 10621 (2025)

Gradient estimates for the porous medium type equations and fast diffusion type equations on complete noncompact metric measure space with compact boundary

Xiangzhi Cao

专题命中 图像生成评测 ：diffusion(title)

Comments The main theorem of this paper is not worth to publish, since the conditions is too strong and meaningless

Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation

Linghao Feng, Dongcheng Zhao, Sicheng Shen, Yiting Dong, Guobin Shen, Yi Zeng

专题命中 图像生成评测 ：image generation(title)