Bitrate Allocation Improvement for Hybrid Animation-Based Face Video Compression

The growing usage of video conferencing and online streaming applications is raising research interest in real-time compression solutions for visual face content. Meanwhile, the performance brought by deep generative network-based compression methods is beginning to get attention from standardization organizations such as Moving Picture Expert Group (MPEG). This paper focuses on generative methods in use for efficient compression of face videos. We analyze the bitrate contribution corresponding to different coded entities in the purpose of optimizing coding efficiency for a recently proposed Generative Face Video Coding (GFVC) scheme. Based on this study, we propose a simple but efficient enhancement of the existing hybrid face video compression, leading to an average of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$10-20{\%}$</tex> Bjøntegaard Delta-rate (BD-Rate) gain over the reference Hybrid Deep Animation Codec (HDAC) method, without further training of the initial model.