C3Net: Demoiréing network attentive in channel, color and concatenation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sangmin | - |
dc.contributor.author | Nam, Hyungjoon | - |
dc.contributor.author | Kim, Jisu | - |
dc.contributor.author | Jeong, Jechang | - |
dc.date.accessioned | 2021-07-30T05:13:41Z | - |
dc.date.available | 2021-07-30T05:13:41Z | - |
dc.date.created | 2021-05-11 | - |
dc.date.issued | 2020-06 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/3722 | - |
dc.description.abstract | Attentive neural networks for image restoration are in the spotlight because they got remarkable results both qualitatively and quantitatively. Networks attentive in RGB channels were effective in fields such as single image super-resolution and RAW to RGB mapping. In addition, networks attentive in positions of pixels were used in image denoising. However, networks attentive in positions of pixels, so called spatial attention or pixel attention algorithm, were not as effective in image restoration because the number of pixels in patches of an image is so many that the weights by sigmoid function are insignificant. Also, networks attentive in positions of pixels were mainly used in high-level vision such as image classification and image captioning where there is no need to restore an image itself. In this paper, we propose a demoiréing network attentive in channel, color, and concatenation, named C3Net. The proposed algorithm uses residual blocks attentive in RGB channels to take advantage of channel attention algorithm. In addition, we introduce a L1 color loss for demoiréing to solve moiré patterns caused by color-striped patterns. Also, we transferred multi-scale information by concatenation, not multiplying with the insignificant weights by sigmoid function. As a result, our proposed C3Net showed state-of-the-art results in the benchmark dataset on NTIRE 2020 demoiréing challenge. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE Computer Society | - |
dc.title | C3Net: Demoiréing network attentive in channel, color and concatenation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Jeong, Jechang | - |
dc.identifier.doi | 10.1109/CVPRW50498.2020.00221 | - |
dc.identifier.scopusid | 2-s2.0-85090131827 | - |
dc.identifier.bibliographicCitation | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, v.2020-June, pp.1713 - 1721 | - |
dc.relation.isPartOf | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops | - |
dc.citation.title | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops | - |
dc.citation.volume | 2020-June | - |
dc.citation.startPage | 1713 | - |
dc.citation.endPage | 1721 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Color | - |
dc.subject.keywordPlus | Computer vision | - |
dc.subject.keywordPlus | Image classification | - |
dc.subject.keywordPlus | Image denoising | - |
dc.subject.keywordPlus | Pixels | - |
dc.subject.keywordPlus | Restoration | - |
dc.subject.keywordPlus | Scales (weighing instruments) | - |
dc.subject.keywordPlus | Benchmark datasets | - |
dc.subject.keywordPlus | High-level visions | - |
dc.subject.keywordPlus | Image captioning | - |
dc.subject.keywordPlus | Multi-scale informations | - |
dc.subject.keywordPlus | Sigmoid function | - |
dc.subject.keywordPlus | Single images | - |
dc.subject.keywordPlus | Spatial attention | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | Image reconstruction | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9150588 | - |
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.