Expression-Controllable Facial Video Generation for Impression Quantification

Abstract

In this study, we propose a method for generating facial videos of various people with various expressions from a single video of a certain person. The proposed method is based on First Order Motion Model (FOMM), but extended to enable to control the facial expression in a generated video by incorporating a mechanism to control facial Expression and gaze direction in FOMM. Besides, in order to save the effort for editing the facial expression on each frame, we also implement a function to interpolate the weight values for each frame from manually assigned weights just for sparse frames. We confirm that the proposed method generates natural facial videos with variously controlled expressions.