AIM 2020 challenge on real image super-resolution: Methods and results

P Wei, H Lu, R Timofte, L Lin, W Zuo, Z Pan, B Li…�- Computer Vision–ECCV�…, 2020 - Springer
P Wei, H Lu, R Timofte, L Lin, W Zuo, Z Pan, B Li, T Xi, Y Fan, G Zhang, J Liu, J Han, E Ding
Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020�…, 2020Springer
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 *� 2, *� 3 and *� 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�…
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 2, 3 and 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.
Springer