Dynamic Range Transformer (DRT): Learning Enhanced Log-Perceptual Information with Swin-Fourier Convolution Network for HDR Imaging
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Heunseung | - |
dc.contributor.author | Shin, Joongchol | - |
dc.contributor.author | Choi, Jinsol | - |
dc.contributor.author | Paik, Joonki | - |
dc.date.accessioned | 2024-02-13T03:00:24Z | - |
dc.date.available | 2024-02-13T03:00:24Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/71926 | - |
dc.description.abstract | The image obtained using an image sensor with limited dynamic range cannot perfectly represent the various lighting conditions of the real world. Various HDR methods have been studied for expanding the dynamic range in a single image. However, it is difficult to avoid ghosting artifacts caused by the movement of the subject over time and the corresponding texture loss. To solve these problems, we present a novel HDR image acquisition method via dynamic range transformer (DrT) that learns enhanced log-perceptual information using Swin-Fourier convolutional neural network as a backbone. When training the DrT with Swin-Fourier network, it estimates the attention map to obtain an HDR image by minimizing the enhanced log-perceptual (ELP) loss. The Swin-Fourier network considers both local and global contexts simultaneously, which reduces ghosting and texture loss. By learning ELP, it also minimizes color distortion and restores fine details of the dynamic range. Experimental results demonstrate that the HDR results obtained using DrT show reduced color distortion, significantly decreased ghosting artifacts, and texture loss compared to conventional methods. We provide implementation code of our proposed methods in https://github.com/HeunSeungLim/DrT © 2023 IEEE. | - |
dc.format.extent | 5 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Dynamic Range Transformer (DRT): Learning Enhanced Log-Perceptual Information with Swin-Fourier Convolution Network for HDR Imaging | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICIP49359.2023.10223189 | - |
dc.identifier.bibliographicCitation | Proceedings - International Conference on Image Processing, ICIP, pp 3040 - 3044 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 001106821003022 | - |
dc.identifier.scopusid | 2-s2.0-85180756927 | - |
dc.citation.endPage | 3044 | - |
dc.citation.startPage | 3040 | - |
dc.citation.title | Proceedings - International Conference on Image Processing, ICIP | - |
dc.type.docType | Proceedings Paper | - |
dc.subject.keywordAuthor | high dynamic range | - |
dc.subject.keywordAuthor | log-Euclidean metric | - |
dc.subject.keywordAuthor | transformer | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
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.