论文标题
翻译您喜欢使用区域归一化的面部区域
Translate the Facial Regions You Like Using Region-Wise Normalization
论文作者
论文摘要
尽管基于GAN（生成的对抗网络）的技术已大大提高了图像合成和面部翻译的性能，但文献中只有很少的作品提供基于区域的样式编码和翻译。我们在本文中提出了一个区域归一化框架，用于区域水平的面部翻译。虽然使用可用方法对每个区域的样式进行编码，但我们构建了一个所谓的RIN（区域标准化）块，将样式单独注入每个区域特征映射，然后将其融合以进行卷积和上升采样。因此，不同区域的形状和纹理都可以转化为各种目标样式。还提出了一个区域匹配损失，以显着减少翻译过程中区域之间的推断。对三个公开可用数据集（即Morph，Rafd和Celebamask-HQ）进行了广泛的实验，这表明我们的方法表明，对Stargan，Sean和Funit等最先进方法有了很大的改进。我们的方法在精确控制要翻译的区域方面具有进一步的优势。结果，可以实现区域级别的表达式变化，并且可以逐步化妆。该视频演示可在https://youtu.be/cerqsbzxafk上获得。
Though GAN (Generative Adversarial Networks) based technique has greatly advanced the performance of image synthesis and face translation, only few works available in literature provide region based style encoding and translation. We propose in this paper a region-wise normalization framework, for region level face translation. While per-region style is encoded using available approach, we build a so called RIN (region-wise normalization) block to individually inject the styles into per-region feature maps and then fuse them for following convolution and upsampling. Both shape and texture of different regions can thus be translated to various target styles. A region matching loss has also been proposed to significantly reduce the inference between regions during the translation process. Extensive experiments on three publicly available datasets, i.e. Morph, RaFD and CelebAMask-HQ, suggest that our approach demonstrate a large improvement over state-of-the-art methods like StarGAN, SEAN and FUNIT. Our approach has further advantages in precise control of the regions to be translated. As a result, region level expression changes and step by step make up can be achieved. The video demo is available at https://youtu.be/ceRqsbzXAfk.
