发表机构
Tongji University; Tencent; Nanyang Technological University; Hong Kong University of Science and Technology（同济大学; 腾讯; 南洋理工大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图像风格缺乏统一定义的问题，提出分层风格定义，构建含多类数据的大规模风格数据集MegaStyle++-8M，扩展了风格空间并提供研究图像风格的可扩展基础。
AI 中文摘要
图像风格是一个高度抽象、由人类构建的概念，受多种视觉因素影响且与内容内在纠缠，但目前仍缺乏统一且明确的图像风格定义。本研究首先探讨“何为风格”这一基本问题，随后提出一种分层风格定义，从整体风格身份到细粒度视觉属性描述图像风格，提供更具结构化、可迁移性和可解释性的风格表示。基于该定义，我们改进了MegaStyle的风格标注流程，并构建了MegaStyle++-8M，这是一个包含15万个整体风格身份、100万条细粒度风格提示及800万张风格化图像的大规模风格数据集。大量分析表明，我们的分层定义在多样性和语义广度上大幅扩展了风格空间，同时精准捕捉参考图像的内在视觉风格。该数据集和代码将在指定的https URL更新，我们希望MegaStyle++为研究和建模多样化图像风格提供可扩展的基础。
英文摘要
Image style is a highly abstract, human-constructed concept shaped by a range of visual factors and intrinsically entangled with content, yet a unified and explicit definition of image style remains lacking. In this work, we first discuss the fundamental question of what is style and then propose a hierarchical style definition that describes image style from an overall style identity to fine-grained visual attributes, providing a more structured, transferable, and interpretable style representation. Based on this definition, we refine the style annotation pipeline of MegaStyle and construct MegaStyle++-8M, a large-scale style dataset containing 150K overall style identities, 1M fine-grained style prompts, and 8M stylized images. Extensive analyses demonstrate that our hierarchical definition substantially expands the style space in both diversity and semantic breadth, while precisely capturing intrinsic visual style of reference images. The dataset and code will be updated at https://github.com/Tencent/MegaStyle, we hope MegaStyle++ provides a scalable foundation for studying and modeling diverse image styles.
CommentsThe dataset and code will be updated at https://github.com/Tencent/MegaStyle, 10pages, 5 figures
