Paper Info
Title
Contrastive learning for a single historical painting's blind super-resolution
Abstract
Most of the existing blind super-resolution(SR) methods explicitly estimate the kernel in pixel space, which usually has a large deviation and results in poor SR performance. As a seminal work, DASR learns abstract representations to distinguish various degradations in the feature space, which effectively reduces degradation estimation bias. Therefore, we also employ the feature space to extract degradation representations for an ancient painting. However, most of the blind SR mehods, including DASR, are committed to removing degradations introduced by kernels, downsampling and additive noise. Among them, downsampling degradation is often accompanied by unpleasant artifacts. To address this issue, the paper designs a high-resolution(HR) representation encoder EHR based on contrastive learning to distinguish artifacts introduced by downsampling. Moreover, to optimize the illposed nature of blind SR, we propose a contrastive regularization(CR) to minimize the contrastive loss based on VGG-19. With the help of CR, the SR images are pulled closer to the HR images and pushed far away from bicubic LR observations. Benefiting from these improvements, our method consistently achieves higher quantitative performance and better visual quality with more natural textures than state-of-the-art approaches on a specialized painting dataset. (C) 2021 The Authors. Published by Elsevier B.V. on behalf of Zhejiang University and Zhejiang University Press Co. Ltd.
Year
DOI
Venue
2021
10.1016/j.visinf.2021.11.002
VISUAL INFORMATICS
Keywords
DocType
Volume
Degradation representation, Blind superresolution, Contrastive learning, Historical painting, Deep learning
Journal
5
Issue
ISSN
Citations 
4
2468-502X
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Hongzhen Shi100.34
Dan Xu220152.67
Kangjian He372.12
Hao Zhang400.34
Yingying Yue500.68