Controllable One-Shot Face Video Synthesis With Semantic Aware Prior
This work improves video conferencing quality by enabling more realistic and controllable face animation, though it is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of one-shot talking-head synthesis by addressing limitations in generation quality for large head poses and capturing fine facial motion details, resulting in improved semantic consistency by 7% in keypoint distance and expression preservation by 15% in emotion embedding distance compared to baselines.
The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame. Recent methods rely on warping the appearance feature extracted from the source, by using motion fields estimated from the sparse keypoints, that are learned in an unsupervised manner. Due to their lightweight formulation, they are suitable for video conferencing with reduced bandwidth. However, based on our study, current methods suffer from two major limitations: 1) unsatisfactory generation quality in the case of large head poses and the existence of observable pose misalignment between the source and the first frame in driving videos. 2) fail to capture fine yet critical face motion details due to the lack of semantic understanding and appropriate face geometry regularization. To address these shortcomings, we propose a novel method that leverages the rich face prior information, the proposed model can generate face videos with improved semantic consistency (improve baseline by $7\%$ in average keypoint distance) and expression-preserving (outperform baseline by $15 \%$ in average emotion embedding distance) under equivalent bandwidth. Additionally, incorporating such prior information provides us with a convenient interface to achieve highly controllable generation in terms of both pose and expression.