The 2018 PIRM Challenge on Perceptual Image Super-resolution
Yochai Blau, Roey Mechrez, Radu Timofte, Tomer Michaeli, Lihi Zelnik-Manor
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/alterzero/STARnetpytorch★ 185
- github.com/alterzero/RBPN-PyTorchpytorch★ 0
- github.com/subeeshvasu/2018_subeesh_epsr_eccvwpytorch★ 0
- github.com/alterzero/DBPN-Pytorchpytorch★ 0
- github.com/idearibosome/tf-perceptual-eusrtf★ 0
- github.com/ryanxingql/image-quality-assessment-toolboxpytorch★ 0
- github.com/lizatish/My_CNNpytorch★ 0
- github.com/shnhrtkyk/satellite-super-resolutionpytorch★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| MSU SR-QA Dataset | PI | SROCC | 0.52 | — | Unverified |