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。

2025-09-12 至 2025-09-12 共收录 4 篇信号源：cs.CV, cs.GR, cs.MM

1. 文生图 4 篇

2509.09680 2025-09-12 cs.CV cs.CL 85%

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

Rongyao Fang, Aldrich Yu, Chengqi Duan, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li

机构 * CUHK（香港中文大学）； HKU（香港大学）； BUAA（北京航空航天大学）； Alibaba（阿里巴巴）

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

Comments Project page: https://flux-reason-6m.github.io/

2509.08940 2025-09-12 cs.CV 83%

Discovering Divergent Representations between Text-to-Image Models

Lisa Dunlap, Joseph E. Gonzalez, Trevor Darrell, Fabian Caba Heilbron, Josef Sivic, Bryan Russell

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

Comments Accepted to ICCV 2025. Code available at https://github.com/adobe-research/CompCon

2509.09488 2025-09-12 cs.CR cs.AI 75%

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts

Felix Mächtle, Ashwath Shetty, Jonas Sander, Nils Loose, Sören Pirk, Thomas Eisenbarth

机构 * Visual Computing and Artificial Intelligence, Kiel University, Germany（视觉计算与人工智能，基尔大学，德国）； Artificial Intelligence, Kiel University, Germany（人工智能，基尔大学，德国）

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

2405.03486 2025-09-12 cs.CR cs.CV cs.SI 57%

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes, Savvas Zannettou, Yang Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）； TU Delft（代尔夫特理工大学）

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

Comments To Appear in the ACM Conference on Computer and Communications Security (CCS), October 13, 2025