Ghost-Free Deep High-Dynamic-Range Imaging Using Focus Pixels for Complex Motion Scenes
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Woo, Sung-Min | - |
dc.contributor.author | Ryu, Je-Ho | - |
dc.contributor.author | Kim, Jong-Ok | - |
dc.date.accessioned | 2021-12-08T05:42:03Z | - |
dc.date.available | 2021-12-08T05:42:03Z | - |
dc.date.created | 2021-08-30 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/130259 | - |
dc.description.abstract | Multi-exposure image fusion inevitably causes ghost artifacts owing to inaccurate image registration. In this study, we propose a deep learning technique for the seamless fusion of multi-exposed low dynamic range (LDR) images using a focus-pixel sensor. For auto-focusing in mobile cameras, a focus-pixel sensor originally provides left (L) and right (R) luminance images simultaneously with a full-resolution RGB image. These L/R images are less saturated than the RGB images because they are summed up to be a normal pixel value in the RGB image of the focus pixel sensor. These two features of the focus pixel image, namely, relatively short exposure and perfect alignment are utilized in this study to provide fusion cues for high dynamic range (HDR) imaging. To minimize fusion artifacts, luminance and chrominance fusions are performed separately in two sub-nets. In a luminance recovery network, two heterogeneous images, the focus pixel image and the corresponding overexposed LDR image, are first fused by joint learning to produce an HDR luminance image. Subsequently, a chrominance network fuses the color components of the misaligned underexposed LDR input to obtain a 3-channel HDR image. Existing deep-neural-network-based HDR fusion methods fuse misaligned multi-exposed inputs directly. They suffer from visual artifacts that are observed mostly in saturated regions because pixel values are clipped out. Meanwhile, the proposed method reconstructs missing luminance with aligned unsaturated focus pixel image first, and thus, the luma-recovered image provides the cues for accurate color fusion. The experimental results show that the proposed method not only accurately restores fine details in saturated areas, but also produce ghost-free high-quality HDR images without pre-alignment. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | FUSION | - |
dc.subject | SUPERRESOLUTION | - |
dc.title | Ghost-Free Deep High-Dynamic-Range Imaging Using Focus Pixels for Complex Motion Scenes | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Jong-Ok | - |
dc.identifier.doi | 10.1109/TIP.2021.3077137 | - |
dc.identifier.scopusid | 2-s2.0-85105856694 | - |
dc.identifier.wosid | 000652060600001 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON IMAGE PROCESSING, v.30, pp.5001 - 5016 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON IMAGE PROCESSING | - |
dc.citation.title | IEEE TRANSACTIONS ON IMAGE PROCESSING | - |
dc.citation.volume | 30 | - |
dc.citation.startPage | 5001 | - |
dc.citation.endPage | 5016 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | FUSION | - |
dc.subject.keywordPlus | SUPERRESOLUTION | - |
dc.subject.keywordAuthor | Image color analysis | - |
dc.subject.keywordAuthor | Image resolution | - |
dc.subject.keywordAuthor | Imaging | - |
dc.subject.keywordAuthor | Dynamic range | - |
dc.subject.keywordAuthor | Cameras | - |
dc.subject.keywordAuthor | Lenses | - |
dc.subject.keywordAuthor | Photonics | - |
dc.subject.keywordAuthor | Disparity | - |
dc.subject.keywordAuthor | focus pixel | - |
dc.subject.keywordAuthor | ghost free imaging | - |
dc.subject.keywordAuthor | high dynamic range | - |
dc.subject.keywordAuthor | joint learning | - |
dc.subject.keywordAuthor | saturation recovery | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea 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.