Document Shadow Removal With Foreground Detection Learning From Fully Synthetic Images

Recent advances in deep neural networks, especially in generative adversarial networks (GAN), have shown remarkable progress in face image generations. However, most of the existing face image generators can only synthesize random face images, but are not able to control the attributes of the generated face images. Though conditional GAN based methods can manipulate the attributes to some extent, but they can only generate low-resolution face images up to 256x256. in this study, based on StyleGAN, one of the state-of-the-art image generators for synthesizing high-quality face images, we propose a simple but efficient approach to generate high-resolution and hyper-realistic face images with any desired attribute. By training an attribute classifier to assign attribute labels to given synthesized face images, we build the links between latent vectors and face attributes. in such a way, the latent vectors can be grouped into different clusters, each cluster corresponding to one face attribute. We then extract the prototypes for each cluster, which are used to control the attribute of the generated face image. Extensive experiments demonstrate the effectiveness of the proposed approach for high-quality face image generation with predefined attributes.