Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth
缺乏指导模型训练的实际目标是一个主要的化妆迁移任务的问题。大多数现有方法通过生成伪真实（PGT）来解决这个问题。然而，生成的PGT通常是次优的，他们的不精确性最终会导致性能下降。为了减轻这个问题，在本文中，我们提出了一个新颖的内容风格解耦化妆迁移（CSD-MT）方法，该方法在纯粹的无监督方式下工作，从而消除了生成PGT的负面影响。具体来说，根据频率特征分析，我们假设面部图像的低频（LF）组件与化妆风格信息更为相关，而高频（HF）组件则与内容细节更为相关。这个假设使得CSD-MT通过频率分解解耦每个面部图像的内容和化妆风格信息。然后，CSD-MT通过最大化输入图像和转移结果之间的这两种信息的一致性来实现化妆迁移。还引入了两个新的损失函数以进一步提高迁移性能。广泛的定量和定性分析证明了我们的CSD-MT方法的有效性。我们的代码可在此处访问：https://www.csdn.net/p/100621200/
The absence of real targets to guide the model training is one of the main problems with the makeup transfer task. Most existing methods tackle this problem by synthesizing pseudo ground truths (PGTs). However, the generated PGTs are often sub-optimal and their imprecision will eventually lead to performance degradation. To alleviate this issue, in this paper, we propose a novel Content-Style Decoupled Makeup Transfer (CSD-MT) method, which works in a purely unsupervised manner and thus eliminates the negative effects of generating PGTs. Specifically, based on the frequency characteristics analysis, we assume that the low-frequency (LF) component of a face image is more associated with its makeup style information, while the high-frequency (HF) component is more related to its content details. This assumption allows CSD-MT to decouple the content and makeup style information in each face image through the frequency decomposition. After that, CSD-MT realizes makeup transfer by maximizing the consistency of these two types of information between the transferred result and input images, respectively. Two newly designed loss functions are also introduced to further improve the transfer performance. Extensive quantitative and qualitative analyses show the effectiveness of our CSD-MT method. Our code is available at this https URL.
https://arxiv.org/abs/2405.17240
https://arxiv.org/pdf/2405.17240.pdf