BeautyREC：健壮、高效且内容保持的补充传输
BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer
摘要：
在这项工作中，我们提出了一个强大的，有效的，和具体的化妆转移方法（简称为BeautyREC）。与利用全局注意力、简单地连接特征或隐式地操纵潜在空间中的特征的现有方法不同，我们提出了一种特定于组件的对应关系，以将参考图像的化妆风格直接转移到对应的组件（例如，皮肤，嘴唇，眼睛）的源图像，使精细和准确的局部化妆转移。作为辅助，引入了Transformer的远程视觉依赖性，以实现有效的全局化妆转移。而不是常用的循环结构，是复杂和不稳定的，我们采用了内容一致性损失加上内容编码器，以实现有效的单路径化妆传输。本研究的关键见解是为局部化妆转移建模组件特定的对应关系，捕获全局化妆转移的长期依赖关系，并通过单路径结构实现高效的化妆转移。我们还贡献了BeautyFace，一个化妆转移数据集，以补充现有的数据集。该数据集包含3，000张面孔，涵盖更多样化的化妆风格，面部姿势和种族。每个面都有注释的解析图。大量的实验证明了我们的方法对国家的最先进的方法的有效性。此外，我们的方法很有吸引力，因为它只有1M个参数，优于最先进的方法（BeautyGAN：8.43M，PSGAN：12.62M，SCGAN：15.30M，CPM：9.24M，SSAT：10.48M）。
英文摘要：
In this work, we propose a Robust, Efficient, and Component-specific makeup transfer method (abbreviated as BeautyREC). A unique departure from prior methods that leverage global attention, simply concatenate features, or implicitly manipulate features in latent space, we propose a component-specific correspondence to directly transfer the makeup style of a reference image to the corresponding components (e.g., skin, lips, eyes) of a source image, making elaborate and accurate local makeup transfer. As an auxiliary, the long-range visual dependencies of Transformer are introduced for effective global makeup transfer. Instead of the commonly used cycle structure that is complex and unstable, we employ a content consistency loss coupled with a content encoder to implement efficient single-path makeup transfer. The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeup transfer, and enabling efficient makeup transfer via a single-path structure. We also contribute BeautyFace, a makeup transfer dataset to supplement existing datasets. This dataset contains 3,000 faces, covering more diverse makeup styles, face poses, and races. Each face has annotated parsing map. Extensive experiments demonstrate the effectiveness of our method against state-of-the-art methods. Besides, our method is appealing as it is with only 1M parameters, outperforming the state-of-the-art methods (BeautyGAN: 8.43M, PSGAN: 12.62M, SCGAN: 15.30M, CPM: 9.24M, SSAT: 10.48M).
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。
