Real-Time Super-Resolution for Real-World Images on Mobile Devices

TL;DR

This paper introduces a real-time super-resolution method for mobile devices that handles diverse real-world degradations, outperforming existing approaches in quality and efficiency.

Contribution

A novel real-time super-resolution approach designed for mobile devices that effectively manages various real-world image degradations.

Findings

Outperforms state-of-the-art methods in PSNR and SSIM

Achieves real-time performance on mobile devices

Handles diverse real-world degradations effectively

Abstract

Image Super-Resolution (ISR), which aims at recovering High-Resolution (HR) images from the corresponding Low-Resolution (LR) counterparts. Although recent progress in ISR has been remarkable. However, they are way too computationally intensive to be deployed on edge devices, since most of the recent approaches are deep learning-based. Besides, these methods always fail in real-world scenes, since most of them adopt a simple fixed "ideal" bicubic downsampling kernel from high-quality images to construct LR/HR training pairs which may lose track of frequency-related details. In this work, an approach for real-time ISR on mobile devices is presented, which is able to deal with a wide range of degradations in real-world scenarios. Extensive experiments on traditional super-resolution datasets (Set5, Set14, BSD100, Urban100, Manga109, DIV2K) and real-world images with a variety of degradations demonstrate that our method outperforms the state-of-art methods, resulting in higher PSNR and SSIM, lower noise and better visual quality. Most importantly, our method achieves real-time performance on mobile or edge devices.