视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-09-05 至 2025-09-05 共收录 6 篇信号源：cs.CV, cs.GR, cs.MM

1. 文生图 6 篇

2509.04446 2025-09-05 cs.CV 88%

Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models

Kiymet Akdemir, Jing Shi, Kushal Kafle, Brian Price, Pinar Yanardag

机构 * Virginia Tech（弗吉尼亚理工大学）； Adobe Research（Adobe研究）

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

2509.04269 2025-09-05 cs.CV 88%

TauGenNet: Plasma-Driven Tau PET Image Synthesis via Text-Guided 3D Diffusion Models

Yuxin Gong, Se-in Jang, Wei Shao, Yi Su, Kuang Gong

机构 * J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida（J. Crayton Pruitt家族生物医学工程系，佛罗里达大学）； Department of Radiology & Biomedical Imaging, Yale University（放射学与生物医学成像系，耶鲁大学）； Department of Medicine, University of Florida（医学系，佛罗里达大学）； Banner Alzheimer’s Institute（Banner阿尔茨海默症研究所）

专题命中文生图：diffusion(title,abstract)；image synthesis(title,abstract)；分类 cs.CV

Comments 9 pages, 4 figures, submitted to IEEE Transactions on Radiation and Plasma Medical Sciences

2504.13392 2025-09-05 cs.CV cs.HC 88%

POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation

Evans Xu Han, Alice Qian Zhang, Haiyi Zhu, Hong Shen, Paul Pu Liang, Jane Hsieh

机构 * Stanford University（斯坦福大学）； Yale University（耶鲁大学）； Carnegie Mellon University（卡内基梅隆大学）； Massachusetts Institute of Technology（麻省理工学院）

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

2411.15537 2025-09-05 cs.CV 77%

MUNBa: Machine Unlearning via Nash Bargaining

Jing Wu, Mehrtash Harandi

机构 * Department of Data Science & AI（数据科学与人工智能系）； Department of Electrical and Computer Systems Engineering（电气与计算机系统工程系）

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

2509.04298 2025-09-05 cs.CV 57%

Noisy Label Refinement with Semantically Reliable Synthetic Images

Yingxuan Li, Jiafeng Mao, Yusuke Matsui

机构 * The University of Tokyo（东京大学）； CyberAgent, Inc.（CyberAgent公司）

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

Comments Accepted to ICIP2025

2410.13287 2025-09-05 cs.LG 50%

PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs

Xiaoyan Hu, Ho-fung Leung, Farzan Farnia

机构 * Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）； Independent Researcher（独立研究者）

专题命中文生图：text-to-image(abstract)

Comments accepted to ICML 2025