AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results

TL;DR

This paper presents the AIM 2020 challenge on real image super-resolution, highlighting diverse methods, results, and the challenge's role in advancing realistic SR techniques for practical applications.

Contribution

It introduces a comprehensive challenge with multiple tracks, encouraging development of SR methods for real-world degraded images and benchmarking state-of-the-art approaches.

Findings

452 participants registered across three tracks

24 teams submitted results

Evaluation based on PSNR and SSIM metrics

Abstract

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.