Visible to the public Ultra-Low Bitrate Video Conferencing Using Deep Image Animation

TitleUltra-Low Bitrate Video Conferencing Using Deep Image Animation
Publication TypeConference Paper
Year of Publication2022
AuthorsKonuko, Goluck, Valenzise, Giuseppe, Lathuilière, Stéphane
Conference Name2022 IEEE International Conference on Image Processing (ICIP)
KeywordsBit rate, Codecs, Deep Learning, deep video, Image coding, Metrics, Model-based compression, Neural networks, pubcrawl, resilience, Resiliency, Scalability, Video compression, Video Conferencing, visualization
Abstract

In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely limited, we adopt a model-based approach that employs deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side. The overall system is trained in an end-to-end fashion minimizing a reconstruction error on the encoder output. Objective and subjective quality evaluation experiments demonstrate that the proposed approach provides an average bitrate reduction for the same visual quality of more than 60% compared to HEVC.

Notes

ISSN: 2381-8549

DOI10.1109/ICIP46576.2022.9897526
Citation Keykonuko_ultra-low_2022