Multiple Facial Expressions Synthesis Driven by Editable Line Maps

Abstract

Facial expression is an important facial semantics on visual aspect. The facial expressions synthesis has a wide range of applications in human-computer interaction and virtual reality. In recent years, image synthesis base on generative adversarial networks(GANs) is developing rapidly. In the image-to-image translation work, we propose a new facial expression generation method base on the idea of conditional GANs and realize the optimization of the generated results. The main work of this paper includes: Editable facial lines map is utilized as a constraint, combining with neutral face images as inputs of generator, so that a variety of facial expression images can be generated by editing the constraints. Correntropy loss of feature matching is added, which is used to measure the intermediate representation between the real images and the generated images by improving the adversarial loss. Consequently, the generated facial expressions can be more realistic. Base on the ideas above, the proposed method needs only one generator to generate different realistic facial images with various expressions.