GRAVITATED LATENT SPACE LOSS GENERATED BY METRIC TENSOR FOR HIGH-DYNAMIC RANGE IMAGING
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Heunseung | - |
dc.contributor.author | Shin, Jungkyoo | - |
dc.contributor.author | Choi, Hyoungki | - |
dc.contributor.author | Kim, Dohoon | - |
dc.contributor.author | Kim, Eunwoo | - |
dc.contributor.author | Paik, Joonki | - |
dc.date.accessioned | 2024-07-12T06:00:20Z | - |
dc.date.available | 2024-07-12T06:00:20Z | - |
dc.date.issued | 2024 | - |
dc.identifier.issn | 0736-7791 | - |
dc.identifier.issn | 1520-6149 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/74720 | - |
dc.description.abstract | High Dynamic Range (HDR) imaging seeks to enhance image quality by combining multiple Low Dynamic Range (LDR) images captured at varying exposure levels. Traditional deep learning approaches often employ reconstruction loss, but this method can lead to ambiguities in feature space during training. To address this issue, we present a new loss function, termed Gravitated Latent Space (GLS) loss, that leverages a metric tensor to introduce a form of virtual gravity within the latent space. This feature helps the model in overcoming saddle points more effectively. Easy to integrate, the GLS loss function fosters stable learning within a convex environment and demonstrates its performance in improving HDR image quality. Experimental data confirms that the proposed method outperforms existing state-of-the-art techniques in quantitative evaluations. © 2024 IEEE. | - |
dc.format.extent | 5 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | GRAVITATED LATENT SPACE LOSS GENERATED BY METRIC TENSOR FOR HIGH-DYNAMIC RANGE IMAGING | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICASSP48485.2024.10448122 | - |
dc.identifier.bibliographicCitation | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp 3300 - 3304 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85195414986 | - |
dc.citation.endPage | 3304 | - |
dc.citation.startPage | 3300 | - |
dc.citation.title | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | - |
dc.type.docType | Conference paper | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | gravitated latent space | - |
dc.subject.keywordAuthor | high dynamic range | - |
dc.subject.keywordAuthor | metric tensor | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.