The 2018 PIRM Challenge on Perceptual Image Super-resolution

TL;DR

The 2018 PIRM challenge evaluated perceptual image super-resolution methods by jointly assessing accuracy and perceptual quality, leading to improved algorithms and insights into quality measures correlating with human opinion.

Contribution

This paper introduces a new evaluation methodology for perceptual super-resolution that balances accuracy and perceptual quality, and reports on the top-performing algorithms from the challenge.

Findings

Top algorithms significantly outperformed previous state-of-the-art in perceptual SR.

Certain image quality measures correlate better with human opinions.

Analysis of current trends in perceptual SR based on challenge submissions.

Abstract

This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018. In contrast to previous SR challenges, our evaluation methodology jointly quantifies accuracy and perceptual quality, therefore enabling perceptual-driven methods to compete alongside algorithms that target PSNR maximization. Twenty-one participating teams introduced algorithms which well-improved upon the existing state-of-the-art methods in perceptual SR, as confirmed by a human opinion study. We also analyze popular image quality measures and draw conclusions regarding which of them correlates best with human opinion scores. We conclude with an analysis of the current trends in perceptual SR, as reflected from the leading submissions.