论文标题
优雅：精美且本地可编辑的gan化妆转移
EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer
论文作者
论文摘要
大多数现有方法将化妆转移视为不同面部区域的颜色分布，而忽略了眼影和腮红等细节。此外，它们仅在预定义的固定区域内实现可控的转移。本文强调了化妆细节和朝着更灵活的控制措施的转移。为此，我们提出了精致且本地可编辑的gan化妆转移（优雅）。它将面部属性编码为金字塔特征图，以保留高频信息。它利用注意力从参考中提取化妆特征并将其调整到源面上，我们引入了一个新颖的SOW注意事项模块，该模块将注意力应用于移动的重叠窗口中以降低计算成本。此外，优雅是第一个通过在功能地图上对应编辑在任意区域内实现定制本地编辑的人。广泛的实验表明，Elegant具有精致的细节并实现最先进的性能，可以产生逼真的妆容面孔。该代码可从https://github.com/chenyu-yang-2000/elegant获得。
Most existing methods view makeup transfer as transferring color distributions of different facial regions and ignore details such as eye shadows and blushes. Besides, they only achieve controllable transfer within predefined fixed regions. This paper emphasizes the transfer of makeup details and steps towards more flexible controls. To this end, we propose Exquisite and locally editable GAN for makeup transfer (EleGANt). It encodes facial attributes into pyramidal feature maps to preserves high-frequency information. It uses attention to extract makeup features from the reference and adapt them to the source face, and we introduce a novel Sow-Attention Module that applies attention within shifted overlapped windows to reduce the computational cost. Moreover, EleGANt is the first to achieve customized local editing within arbitrary areas by corresponding editing on the feature maps. Extensive experiments demonstrate that EleGANt generates realistic makeup faces with exquisite details and achieves state-of-the-art performance. The code is available at https://github.com/Chenyu-Yang-2000/EleGANt.
