The technique of facial attribute manipulation has found increasing application, but it remains challenging to restrict editing of attributes so that a face’s unique details are preserved. In this paper, we introduce our method, which we call a mask-adversarial autoencoder (M-AAE). It combines a variational autoencoder (VAE) and a generative adversarial network (GAN) for photorealistic image generation. We use partial dilated layers to modify a few pixels in the feature maps of an encoder, changing the attribute strength continuously without hindering global information. Our training objectives for the VAE and GAN are reinforced by supervision of face recognition loss and cycle consistency loss, to faithfully preserve facial details. Moreover, we generate facial masks to enforce background consistency, which allows our training to focus on the foreground face rather than the background. Experimental results demonstrate that our method can generate high-quality images with varying attributes, and outperforms existing methods in detail preservation.

面部属性操纵技术已得到越来越多的应用，但是限制属性的编辑以保留面部的独特细节仍然是一项挑战。在本文中，我们介绍了我们的方法，我们称其为“掩模对抗自动编码器”（M-AAE）。它结合了变分自动编码器（VAE）和生成对抗网络（GAN），用于生成逼真的图像。我们使用局部膨胀层来修改编码器特征图中的一些像素，从而在不影响全局信息的情况下连续更改属性强度。我们对VAE和GAN的培训目标通过监督人脸识别损失和循环一致性损失得到加强，以忠实地保留面部细节。此外，我们生成面罩以增强背景一致性，这使我们的训练可以将注意力集中在前景脸部而不是背景上。实验结果表明，该方法能够生成具有不同属性的高质量图像，并且在细节保存方面优于现有方法。