FAIVConf: Face enhancement for AI-based Video Conference with Low Bit-rate
This addresses the challenge of efficient video conferencing for users in bandwidth-limited scenarios, though it is incremental as it builds on existing face generation methods.
The paper tackles the problem of high-quality video conferencing with low bit-rate transmission by proposing FAIVConf, a video compression framework that uses neural face generation techniques to achieve significant bit-rate reduction and better visual quality compared to H.264 and H.265.
Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem. We propose FAIVConf, a specially designed video compression framework for video conferencing, based on the effective neural human face generation techniques. FAIVConf brings together several designs to improve the system robustness in real video conference scenarios: face-swapping to avoid artifacts in background animation; facial blurring to decrease transmission bit-rate and maintain the quality of extracted facial landmarks; and dynamic source update for face view interpolation to accommodate a large range of head poses. Our method achieves a significant bit-rate reduction in the video conference and gives much better visual quality under the same bit-rate compared with H.264 and H.265 coding schemes.