Ultra-low bitrate video conferencing using deep image animation
This work addresses the problem of extremely limited bandwidth for video conferencing applications, providing a significant improvement in bitrate efficiency for users in such conditions.
This paper proposes a deep learning approach for ultra-low bitrate video conferencing. It encodes motion as keypoint displacement and reconstructs video, achieving over 80% bitrate reduction compared to HEVC for the same visual quality.
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 80% compared to HEVC.