Real-Time Neural Video Recovery and Enhancement on Mobile Devices

TL;DR

This paper introduces a real-time neural video recovery and enhancement system optimized for mobile devices, capable of handling frame loss and super-resolution to improve streaming quality across various networks.

Contribution

It presents a novel combined approach including frame recovery, super-resolution, and bitrate adaptation, specifically designed for real-time mobile video enhancement.

Findings

Supports 30 FPS on an iPhone 12

Achieves 24-82% improvement in video QoE

Effective across WiFi, 3G, 4G, and 5G networks

Abstract

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.