MagicStyle：基于参考图像的人像风格化
MagicStyle: Portrait Stylization Based on Reference Image
AI总结：
针对人像参考图像风格化中细节保留与风格迁移难兼顾的问题，提出含CSDI和FFF两阶段的MagicStyle方法，通过存储并融合自注意力特征实现风格化，经实验验证有效。
摘要：
扩散模型的发展极大推动了图像风格化研究，尤其是基于给定风格图像对内容图像进行风格化的方向，吸引了众多学者。该参考图像风格化任务的核心挑战在于，如何在融入风格图像色彩与纹理特征的同时，保留内容图像的细节。当内容图像是纹理细节复杂的人像时，这一挑战会更加突出。为解决该问题，我们提出了一种基于扩散模型、专门面向人像的参考图像风格化方法，名为MagicStyle。MagicStyle包含两个阶段：内容与风格DDIM反演（CSDI）和特征融合前向（FFF）。CSDI阶段为反向去噪过程，分别对内容图像和风格图像执行DDIM Inversion（去噪扩散隐式模型反演），在反演过程中存储两张图像的自注意力查询、键和值特征。FFF阶段执行前向去噪，基于我们精心设计的特征融合注意力（FFA），将预存特征查询、键和值中的纹理与色彩信息和谐融入扩散生成过程。我们开展了全面的对比实验和消融实验，以验证所提出的MagicStyle和FFA的有效性。
英文摘要：
The development of diffusion models has significantly advanced the research on image stylization, particularly in the area of stylizing a content image based on a given style image, which has attracted many scholars. The main challenge in this reference image stylization task lies in how to maintain the details of the content image while incorporating the color and texture features of the style image. This challenge becomes even more pronounced when the content image is a portrait which has complex textural details. To address this challenge, we propose a diffusion model-based reference image stylization method specifically for portraits, called MagicStyle. MagicStyle consists of two phases: Content and Style DDIM Inversion (CSDI) and Feature Fusion Forward (FFF). The CSDI phase involves a reverse denoising process, where DDIM Inversion is performed separately on the content image and the style image, storing the self-attention query, key and value features of both images during the inversion process. The FFF phase executes forward denoising, harmoniously integrating the texture and color information from the pre-stored feature queries, keys and values into the diffusion generation process based on our Well-designed Feature Fusion Attention (FFA). We conducted comprehensive comparative and ablation experiments to validate the effectiveness of our proposed MagicStyle and FFA.
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。
