Real-Time Neural Video Recovery and Enhancement on Mobile Devices
This work addresses the challenge of optimizing video streaming for mobile users by enabling real-time enhancement, which is incremental as it builds on existing deep learning techniques but integrates them for practical deployment.
The paper tackles the problem of real-time video enhancement on mobile devices by introducing a novel approach that combines video frame recovery, super-resolution, and bit rate adaptation, achieving 30 FPS on an iPhone 12 and increasing video Quality of Experience by 24% to 82% in various network conditions.
As mobile devices become increasingly popular for video streaming, it's crucial to optimize the streaming experience for these devices. Although deep learning-based video enhancement techniques are gaining attention, most of them cannot support real-time enhancement on mobile devices. Additionally, many of these techniques are focused solely on super-resolution and cannot handle partial or complete loss or corruption of video frames, which is common on the Internet and wireless networks. To overcome these challenges, we present a novel approach in this paper. Our approach consists of (i) a novel video frame recovery scheme, (ii) a new super-resolution algorithm, and (iii) a receiver enhancement-aware video bit rate adaptation algorithm. We have implemented our approach on an iPhone 12, and it can support 30 frames per second (FPS). We have evaluated our approach in various networks such as WiFi, 3G, 4G, and 5G networks. Our evaluation shows that our approach enables real-time enhancement and results in a significant increase in video QoE (Quality of Experience) of 24\% - 82\% in our video streaming system.