OmniStyle2：通过学习去风格化来学习风格化
OmniStyle2: Learning to Stylize by Learning to Destylize
AI总结：
OmniStyle2通过逆向学习去风格化来提升风格化质量，提出DeStylePipe框架与DestyleCoT-Filter模块，构建DeStyle-350K数据集并设计BCS-Bench基准，验证去风格化作为可靠监督范式。
摘要：
本文介绍了一种可扩展的监督风格迁移范式，通过逆向问题：不直接学习风格化，而是学习去风格化，从而从艺术图像中去除风格元素以恢复自然图像，生成大规模真实对齐的训练对。为此，我们提出DeStylePipe，一种渐进、多阶段的去风格化框架，从全局通用去风格化开始，逐步发展到类别指令适应，最终部署专门的模型适应以处理复杂风格。紧密集成在此流程中的DestyleCoT-Filter利用链式推理评估每阶段的内容保留和风格去除，将挑战样本向前路由并丢弃持续低质量的配对。基于此框架，我们构建了DeStyle-350K，一个对齐多样艺术风格与其底层内容的大型数据集。我们进一步引入BCS-Bench，一个具有平衡内容通用性和风格多样性的基准，用于系统评估。大量实验表明，训练于DeStyle-350K的模型在风格化质量上表现优异，验证了去风格化作为可靠且可扩展的监督范式。
英文摘要：
This paper introduces a scalable paradigm for supervised style transfer by inverting the problem: instead of learning to stylize directly, we learn to destylize, reducing stylistic elements from artistic images to recover their natural counterparts and thereby producing authentic, pixel-aligned training pairs at scale. To realize this paradigm, we propose DeStylePipe, a progressive, multi-stage destylization framework that begins with global general destylization, advances to category-wise instruction adaptation, and ultimately deploys specialized model adaptation for complex styles that prompt engineering alone cannot handle. Tightly integrated into this pipeline, DestyleCoT-Filter employs Chain-of-Thought reasoning to assess content preservation and style removal at each stage, routing challenging samples forward while discarding persistently low-quality pairs. Built on this framework, we construct DeStyle-350K, a large-scale dataset aligning diverse artistic styles with their underlying content. We further introduce BCS-Bench, a benchmark featuring balanced content generality and style diversity for systematic evaluation. Extensive experiments demonstrate that models trained on DeStyle-350K achieve superior stylization quality, validating destylization as a reliable and scalable supervision paradigm for style transfer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
