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 \wrt 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.

References in corpus (9)

• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Blind Super-Resolution Kernel Estimation using an Internal-GAN
• Residual Non-local Attention Networks for Image Restoration
• CycleGAN, a Master of Steganography
• Densely Connected High Order Residual Network for Single Frame Image Super Resolution
• PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
• Camera Lens Super-Resolution
• Unsupervised Image Super-Resolution with an Indirect Supervised Path

Cited by in corpus (1)

• Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution