Ajou University repository

SimUSR: A simple but strong baseline for unsupervised image super-resolutionoa mark
Citations

SCOPUS

0

Citation Export

Publication Year
2020-06-01
Journal
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher
IEEE Computer Society
Citation
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Vol.2020-June, pp.1953-1961
Mesh Keyword
High resolution imageImage super resolutionsLow resolution imagesState of the artSuper resolutionSupervised learning problemsTraining phaseUnsupervised method
All Science Classification Codes (ASJC)
Computer Vision and Pattern RecognitionElectrical and Electronic Engineering
Abstract
In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relatively easy to collect compared to high resolution (HR) images. By allowing multiple LR images, we build a set of pseudo pairs by denoising and downsampling LR images and cast the original unsupervised problem into a supervised learning problem but in one level lower. Though this line of study is easy to think of and thus should have been investigated prior to any complicated unsupervised methods, surprisingly, there are currently none. Even more, we show that this simple method outperforms the state-of- the-art unsupervised method with a dramatically shorter latency at runtime, and significantly reduces the gap to the HR supervised models. We submitted our method in NTIRE 2020 super-resolution challenge and won 1st in PSNR, 2nd in SSIM, and 13th in LPIPS. This simple method should be used as the baseline to beat in the future, especially when multiple LR images are allowed during the training phase. However, even in the zero-shot condition, we argue that this method can serve as a useful baseline to see the gap between supervised and unsupervised frameworks.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36564
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85090149945&origin=inward
DOI
https://doi.org/10.1109/cvprw50498.2020.00245
Journal URL
http://ieeexplore.ieee.org/xpl/conferences.jsp
Type
Conference
Funding
Acknowledgement. This work was supported by NAVER Corporation and also by the National Research Foundation of Korea grant funded by the Korea government (MSIT) (no.NRF-2019R1A2C1006608)
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.