Abstract

Identity-preserved face beauty transformation aims to change the beauty scale of a face image while preserving the identity of the original face. In our framework of conditional generative adversarial networks (cGANs), the synthesized face produced by the generator would have the same beauty scale indicated by the input condition. Unlike the discrete class labels used in most cGANs, the condition of target beauty scale in our framework is given by a continuous real-valued beauty score in the range [1–5], which makes the work challenging. To tackle the problem, we have implemented a triple structure, in which the conditional discriminator is divided into a normal discriminator and a separate face beauty predictor. We have also developed another new structure called Conditioned Instance Normalization to replace the original concatenation used in cGANs, which makes the combination of the input image and condition more effective. Furthermore, self-consistency loss is introduced as a new parameter to improve the stability of training and quality of the generated image. In the end, the objectives of beauty transformation and identity preservation are evaluated by the pretrained face beauty predictor and state-of-the-art face recognition network. The result is encouraging, and it also shows that certain facial features could be synthesized by the generator according to the target beauty scale, while preserving the original identity.

中文翻译：

---

具有条件生成对抗网络的身份保留面部美容转换

摘要

保留身份的人脸美容变换旨在改变人脸图像的美丽尺度，同时保留原始人脸的身份。在我们的条件生成对抗网络 (cGAN) 框架中，生成器生成的合成人脸将具有与输入条件相同的美感尺度。与大多数 cGAN 中使用的离散类标签不同，我们框架中的目标美容量表的条件由 [1-5] 范围内的连续实值美容评分给出，这使得工作具有挑战性。为了解决这个问题，我们实现了三重结构，其中条件判别器分为正常判别器和单独的面部美容预测器。我们还开发了另一种称为 Conditioned Instance Normalization 的新结构来替代 cGAN 中使用的原始串联，这使得输入图像和条件的组合更加有效。此外，引入了自洽损失作为新参数，以提高训练的稳定性和生成图像的质量。最后，通过预训练的人脸美容预测器和最先进的人脸识别网络来评估美容转换和身份保存的目标。结果令人鼓舞，也表明生成器可以根据目标美貌尺度合成某些面部特征，同时保留原始身份。self-consistency loss作为一个新的参数被引入，以提高训练的稳定性和生成图像的质量。最后，通过预训练的人脸美容预测器和最先进的人脸识别网络来评估美容转换和身份保存的目标。结果令人鼓舞，也表明生成器可以根据目标美貌尺度合成某些面部特征，同时保留原始身份。self-consistency loss作为一个新的参数被引入，以提高训练的稳定性和生成图像的质量。最后，通过预训练的人脸美容预测器和最先进的人脸识别网络来评估美容转换和身份保存的目标。结果令人鼓舞，也表明生成器可以根据目标美貌尺度合成某些面部特征，同时保留原始身份。