Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Seobin | - |
dc.contributor.author | Kim, Dongjin | - |
dc.contributor.author | Baik, Sungyong | - |
dc.contributor.author | Kim, Tae Hyun | - |
dc.date.accessioned | 2023-11-14T08:14:55Z | - |
dc.date.available | 2023-11-14T08:14:55Z | - |
dc.date.created | 2023-11-01 | - |
dc.date.issued | 2023-07 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192168 | - |
dc.description.abstract | Recent deep-learning-based super-resolution (SR) methods have been successful in recovering high-resolution (HR) images from their low-resolution (LR) counterparts, albeit on the synthetic and simple degradation setting: bicubic downscaling. On the other hand, super-resolution on real-world images demands the capability to handle complex downscaling mechanism which produces different artifacts (e.g., noise, blur, color distortion) upon downscaling factors. To account for complex downscaling mechanism in real-world LR images, there have been a few efforts in constructing datasets consisting of LR images with real-world downsampling degradation. However, making such datasets entails a tremendous amount of time and effort, thereby resorting to very few number of downscaling factors (e.g., ×2, ×3, ×4). To remedy the issue, we propose to generate realistic SR datasets for unseen degradation levels by exploring the latent space of real LR images and thereby producing more diverse yet realistic LR images with complex real-world artifacts. Our quantitative and qualitative experiments demonstrate the accuracy of the generated LR images, and we show that the various conventional SR networks trained with our newly generated SR datasets can produce much better HR images. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | ML Research Press | - |
dc.title | Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Dongjin | - |
dc.contributor.affiliatedAuthor | Baik, Sungyong | - |
dc.contributor.affiliatedAuthor | Kim, Tae Hyun | - |
dc.identifier.doi | 10.5555/3618408.3619539 | - |
dc.identifier.scopusid | 2-s2.0-85174421502 | - |
dc.identifier.bibliographicCitation | Proceedings of Machine Learning Research, v.202, no.1131, pp.27188 - 27203 | - |
dc.relation.isPartOf | Proceedings of Machine Learning Research | - |
dc.citation.title | Proceedings of Machine Learning Research | - |
dc.citation.volume | 202 | - |
dc.citation.number | 1131 | - |
dc.citation.startPage | 27188 | - |
dc.citation.endPage | 27203 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Constrained flow | - |
dc.subject.keywordPlus | Controllable degradation | - |
dc.subject.keywordPlus | Down-scaling | - |
dc.subject.keywordPlus | High-resolution images | - |
dc.subject.keywordPlus | Learning-based super-resolution | - |
dc.subject.keywordPlus | Low resolution images | - |
dc.subject.keywordPlus | Lower resolution | - |
dc.subject.keywordPlus | Real-world | - |
dc.subject.keywordPlus | Superresolution | - |
dc.subject.keywordPlus | Superresolution methods | - |
dc.identifier.url | https://dl.acm.org/doi/10.5555/3618408.3619539 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.