SARA：基于空间对齐与区域自适应归一化的可控妆容迁移
SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
AI总结：
针对现有妆容迁移方法缺乏精细风格控制、难应对大空间错位的问题，提出含空间对齐、区域自适应归一化、妆容融合三模块的SARA方法，实现部位与色号可控的高质量迁移，在两个公开数据集上达SOTA。
摘要：
妆容迁移是将参考图像的妆容风格迁移到源图像，同时保留源图像身份特征的过程。该技术应用需求广泛，具备诸多应用场景。但现有方法缺乏对妆容风格的精细控制，在处理较大空间错位时难以获得高质量结果。为解决这一问题，本文提出一种新型空间对齐与区域自适应归一化方法（SARA）。该方法可生成精细的妆容迁移结果，能够应对较大空间错位，实现部位专属、色号可控的妆容迁移。具体而言，SARA包含三个模块：第一，空间对齐模块，用于保留妆容的空间上下文，并提供目标语义图以引导与形状无关的风格编码；第二，区域自适应归一化模块，通过逐区域编码与归一化解耦形状与妆容风格，助力消除空间错位；第三，妆容融合模块，通过注入学习到的尺度与偏置参数，融合身份特征与妆容风格。实验结果表明，本文提出的SARA方法性能优于现有方法，在两个公开数据集上达到了当前最优水平。
英文摘要：
Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing methods lack fine-level control of the makeup style, making it challenging to achieve high-quality results when dealing with large spatial misalignments. To address this problem, we propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper. Our method generates detailed makeup transfer results that can handle large spatial misalignments and achieve part-specific and shade-controllable makeup transfer. Specifically, SARA comprises three modules: Firstly, a spatial alignment module that preserves the spatial context of makeup and provides a target semantic map for guiding the shape-independent style codes. Secondly, a region-adaptive normalization module that decouples shape and makeup style using per-region encoding and normalization, which facilitates the elimination of spatial misalignments. Lastly, a makeup fusion module blends identity features and makeup style by injecting learned scale and bias parameters. Experimental results show that our SARA method outperforms existing methods and achieves state-of-the-art performance on two public datasets.
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。
