A keypoints-motion-based landmark transfer method for face reenactment

Abstract

Face reenactment is a task to transfer the facial pose and expression from one driving face to the source face. It can be done by adding many condition information, such as the landmark, 3D Morphable Model(3DMM). Because the landmark information is easy to get and contains face structure and expression information, many works rely on it. One of the key points for the landmark-based method is to generate landmarks that keep the face shape of the source image while having the same expression and pose as the driving image. Concentrating on this problem, we propose a novel and effective method to transfer the expression and pose based on the motion of the key points between driving images. Besides, we also try to improve the fit ability of the current popular backbone by adding an enhancement module.