arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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 3 信号源:cs.CV, cs.GR, cs.MM

1. 可控生成 3 篇

2507.22627 2025-09-05 cs.CV cs.AI 83%

LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing

Federico Girella, Davide Talon, Ziyue Liu, Zanxi Ruan, Yiming Wang, Marco Cristani

机构 * University of Verona(威尼斯大学) Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会) Polytechnic Institute of Turin(都灵理工学院) University of Reykjavik(雷克雅未克大学)

专题命中 可控生成 :image generation(title,abstract);diffusion(abstract);分类 cs.CV

Comments Accepted at ICCV25 (Oral). Project page: https://intelligolabs.github.io/lots/

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.06002 2025-09-05 cs.CV 57%

Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance

Quang-Huy Che, Duc-Tri Le, Bich-Nga Pham, Duc-Khai Lam, Vinh-Tiep Nguyen

机构 * University of Information Technology(信息技术大学) Vietnam National University(越南国家大学)

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

Comments Published in ICPRAM 2025, ISBN 978-989-758-730-6, ISSN 2184-4313

Journal ref Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM (2025) 251-262

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08570 2025-09-05 cs.SD cs.AI cs.LG eess.AS 50%

Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

Or Tal, Felix Kreuk, Yossi Adi

机构 * The Hebrew University(希伯来大学) Meta Fundamental AI Research(Meta 基础人工智能研究)

专题命中 可控生成 :inpainting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏