图像生成 - arXivDaily 专题

2510.23974 2025-10-29 cs.LG cs.AI 89%

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Byeonghu Na, Minsang Park, Gyuwon Sim, Donghyeok Shin, HeeSun Bae, Mina Kang, Se Jung Kwon, Wanmo Kang, Il-Chul Moon

机构 * KAIST（韩国科学技术院）； NAVER Cloud（NAVER云）

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image editing(abstract)

Comments Accepted at NeurIPS 2025

2510.24012 2025-10-29 cs.LG cs.AI 88%

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Byeonghu Na, Mina Kang, Jiseok Kwak, Minsang Park, Jiwoo Shin, SeJoon Jun, Gayoung Lee, Jin-Hwa Kim, Il-Chul Moon

机构 * KAIST（韩国科学技术院）； NAVER AI Lab（NAVER人工智能实验室）； SNU AIIS（首尔国立大学人工智能研究所）

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)

Comments Accepted at NeurIPS 2025

2510.24034 2025-10-29 cs.CV 79%

AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts

Yufan Liu, Wanqian Zhang, Huashan Chen, Lin Wang, Xiaojun Jia, Zheng Lin, Weiping Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）； School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院）； Nanyang Technological University（南洋理工大学）

专题命中文生图：text-to-image(title,abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

2510.24640 2025-10-29 cs.CV 77%

A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries

Xin Zhang, Yuqi Song, Fei Zuo

机构 * Computer Science Department University of Southern Maine Portland, United States（计算机科学系俄亥俄州立大学帕斯托市美国）； The Department of Computer Science University of Central Oklahoma Edmond, United States（计算机科学系中央俄克拉荷马大学埃德蒙德美国）

专题命中文生图：text-to-image(abstract)；diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

2505.05229 2025-10-29 cs.CV cs.MM 62%

Does CLIP perceive art the same way we do?

Andrea Asperti, Leonardo Dessì, Maria Chiara Tonetti, Nico Wu

机构 * Dept. of Informatics (DISI) University of Bologna（信息学院（DISI）博洛尼亚大学）

专题命中文生图：image synthesis(abstract)；分类 cs.CV、cs.MM

Journal ref Proceedings of IEEE International Conference on Content-Based Multimedia Indexing (IEEE CBMI 2025), Dublin, Ireland, 22-24 October 2025

2510.24278 2025-10-29 cs.CV cs.AI 57%

Training-free Source Attribution of AI-generated Images via Resynthesis

Pietro Bongini, Valentina Molinari, Andrea Costanzo, Benedetta Tondi, Mauro Barni

机构 * University of Siena, Department of Information Engineering and Mathematics（锡耶纳大学信息工程与数学系）； IMT School（IMT学院）

专题命中文生图：text-to-image(abstract)；分类 cs.CV

Comments 14 pages, 4 figures, 1 table, accepted at "The 17th IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS2025)", Perth, Australia

1. 文生图 6 篇