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

Abstract

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches w.r.t. a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution.To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

Deep Learning for Image/Video Restoration and Super-resolution

“…AIM 2019 (Lugmayr et al, 2019) and NTIRE 2020 (Lugmayr et al, 2020a) real-world SR challenges were designed according to the realworld image acquisition setting, i.e., the blur kernel was unknown and no paired LR-HR images were provided.…”

“…In NTIRE 2020 (Lugmayr et al, 2020a), a set of images from the LR source domain and a set of unpaired HR images from the target domain were provided. In Track 1, the aim is to super-resolve images with synthetically generated image processing artifacts, which allows for quantitative benchmarking of the approaches compared to a groundtruth image.…”