Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
- Authors
- Park, Seobin; Kim, Dongjin; Baik, Sungyong; Kim, Tae Hyun
- Issue Date
- Jul-2023
- Publisher
- ML Research Press
- Citation
- Proceedings of Machine Learning Research, v.202, no.1131, pp.27188 - 27203
- Indexed
- SCOPUS
- Journal Title
- Proceedings of Machine Learning Research
- Volume
- 202
- Number
- 1131
- Start Page
- 27188
- End Page
- 27203
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192168
- DOI
- 10.5555/3618408.3619539
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.