Global and Local Attention-Based Free-Form Image Inpainting
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Uddin, S.M.N. | - |
dc.contributor.author | Jung, Yong Ju | - |
dc.date.available | 2020-08-13T01:35:54Z | - |
dc.date.created | 2020-06-15 | - |
dc.date.issued | 2020-06 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/77458 | - |
dc.description.abstract | Deep-learning-based image inpainting methods have shown significant promise in both rectangular and irregular holes. However, the inpainting of irregular holes presents numerous challenges owing to uncertainties in their shapes and locations. When depending solely on convolutional neural network (CNN) or adversarial supervision, plausible inpainting results cannot be guaranteed because irregular holes need attention-based guidance for retrieving information for content generation. In this paper, we propose two new attention mechanisms, namely a mask pruning-based global attention module and a global and local attention module to obtain global dependency information and the local similarity information among the features for refined results. The proposed method is evaluated using state-of-the-art methods, and the experimental results show that our method outperforms the existing methods in both quantitative and qualitative measures. © 2020 by the authors. Licensee MDPI, Basel, Switzerland. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | MDPI | - |
dc.relation.isPartOf | Sensors | - |
dc.title | Global and Local Attention-Based Free-Form Image Inpainting | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000552737900197 | - |
dc.identifier.doi | 10.3390/s20113204 | - |
dc.identifier.bibliographicCitation | Sensors, v.20, no.11, pp.1 - 27 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85086297782 | - |
dc.citation.endPage | 27 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | Sensors | - |
dc.citation.volume | 20 | - |
dc.citation.number | 11 | - |
dc.contributor.affiliatedAuthor | Uddin, S.M.N. | - |
dc.contributor.affiliatedAuthor | Jung, Yong Ju | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Attention module | - |
dc.subject.keywordAuthor | Convolutional neural networks (CNN) | - |
dc.subject.keywordAuthor | Free-form mask | - |
dc.subject.keywordAuthor | Image inpainting | - |
dc.subject.keywordAuthor | Mask update | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Attention mechanisms | - |
dc.subject.keywordPlus | Dependency informations | - |
dc.subject.keywordPlus | Freeforms | - |
dc.subject.keywordPlus | Image Inpainting | - |
dc.subject.keywordPlus | Inpainting | - |
dc.subject.keywordPlus | Local similarity | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Image processing | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon University All Rights Reserved.
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.