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

By Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, S. Chun and 36 more. 2020

190 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

SRFlow: Learning the Super-Resolution Space with Normalizing Flow (2020, background): “Since our aim is perceptual quality, we consider LPIPS the primary metric, as it has been shown to correlate much better with human opinions [28,55].”
Real-World Super-Resolution via Kernel Estimation and Noise Injection (2020, background): “Recently, a series of real-world super-resolution challenges [25, 26] have attracted many participants.”
Unsupervised Image Super-Resolution with an Indirect Supervised Path (2019, methodology): “In addition, to demonstrate the effectiveness of our framework on real-world degradations, we also participated NTIRE2020 Real-World Super-Resolution [23] challenge.”
Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “More recently, Ji et al. [98] take this idea one step further and develop an effective degradation framework using various realistic blur kernels and noise distributions, winning the NTIRE 2020 Challenge on Real-World Image Super-Resolution [122].”
Evaluation and development of deep neural networks for image super-resolution in optical microscopy (2021, background): “Thus, it allows continuous capture of the reorganization of nucleoids during the mitochondrial membrane dynamics of dividing, coalescing and cristae deformation (Supplementary Video 6).”
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results (2020, methodology): “The setting is similar to that from the NTIRE 2019 challenge on real image super-resolution [3] employing RealSR dataset [4], and is different from the AIM 2019 [25] and NTIRE 2020 [24] challenges on real-world super-resolution where no LR-HR pairs are available for training, therefore an unsupervis”