StyleGallery: 无需训练且语义感知的任意图像参考个性化风格迁移
StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References
AI总结：
StyleGallery通过语义感知和无需训练的框架，实现任意图像参考的个性化风格迁移，提升内容保留与风格化平衡能力。
摘要：
尽管在基于扩散的图像风格迁移方面取得了进展，现有方法通常受限于三个方面：1) 语义间隙：风格参考可能遗漏适当的语义内容，导致无法控制的风格化；2) 依赖额外约束（例如语义掩码）限制了适用性；3) 刚性的特征关联缺乏自适应的全局-局部对齐，无法在细粒度风格化和全局内容保留之间取得平衡。这些限制，尤其是无法灵活利用风格输入，从根本上限制了风格迁移在个性化、准确性和适应性方面的表现。为了解决这些问题，我们提出了StyleGallery，一个无需训练且语义感知的框架，支持任意参考图像作为输入，并能够实现有效的个性化定制。它包含三个核心阶段：语义区域分割（在潜在扩散特征上进行自适应聚类以划分区域，无需额外输入）；聚类区域匹配（在提取的特征上进行块过滤以实现精确对齐）；以及风格迁移优化（基于能量函数引导的扩散采样，结合区域风格损失以优化风格化）。在我们引入的基准测试中，实验表明StyleGallery在内容结构保留、区域风格化、可解释性和个性化定制方面均优于最先进的方法，尤其是在利用多个风格参考时。
英文摘要：
Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) reliance on extra constraints (e.g., semantic masks) restricting applicability; 3) rigid feature associations lacking adaptive global-local alignment, failing to balance fine-grained stylization and global content preservation. These limitations, particularly the inability to flexibly leverage style inputs, fundamentally restrict style transfer in terms of personalization, accuracy, and adaptability. To address these, we propose StyleGallery, a training-free and semantic-aware framework that supports arbitrary reference images as input and enables effective personalized customization. It comprises three core stages: semantic region segmentation (adaptive clustering on latent diffusion features to divide regions without extra inputs); clustered region matching (block filtering on extracted features for precise alignment); and style transfer optimization (energy function-guided diffusion sampling with regional style loss to optimize stylization). Experiments on our introduced benchmark demonstrate that StyleGallery outperforms state-of-the-art methods in content structure preservation, regional stylization, interpretability, and personalized customization, particularly when leveraging multiple style references.
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。
