Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report

Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services. While many solutions have been proposed for this task, the majority of them are too computationally expensive to run on portable devices with limited hardware resources. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a real-time performance on mobile GPUs. The participants were provided with the REDS dataset and trained their models to do an efficient 4X video upscaling. The runtime of all models was evaluated on the OPPO Find X2 smartphone with the Snapdragon 865 SoC capable of accelerating floating-point networks on its Adreno GPU. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

1. Introduction

An increased popularity of various video streaming services and a widespread of mobile devices have created a strong need for efficient and mobile-friendly video super-resolution approaches. Over the past years, many accurate deep learning-based solutions have been proposed for this problem [46], [48], [57], [37], [51], [50], [12]. The biggest limitation of these methods is that they were primarily targeted at achieving high fidelity scores while not optimized for computational efficiency and mobile-related constraints, which is essential for tasks related to image [18], [19], [32] and video [47] enhancement on mobile devices. In this challenge, we take one step further in solving this problem by using a popular REDS [46] video super-resolution dataset and by imposing additional efficiency-related constraints on the developed solutions.