File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Light field image restoration in low-light environment

TitleLight field image restoration in low-light environment
Authors
Issue Date2020
PublisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml?WT.svl=mddp2
Citation
Proceedings of SPIE, v. 11525: SPIE Future Sensing Technologies Conference, Virtual Meeting, Japan, 9-13 November 2020, paper 11525 1H How to Cite?
AbstractLight field (LF) imaging provides rich spatial and angular information, but is problematic in low-light environment as the images suffer from low contrast and visibility. In this paper, we present a learning-based method to enhance low-light LF images. A high-dimensional convolutional neural network (CNN) is introduced to extract the spatio-angular features from the LF. The network operates directly on the four-dimensional LF data rather than on individual sub-aperture images, avoiding the loss of geometric information. Color compensation is then performed on the enhanced LF images coming from the high-dimensional CNN to reduce color distortion. The experimental results show that the proposed method achieves noticeable improvement compared with state-of-the-art low-light image restoration techniques in both visual inspection and objective assessments.
Persistent Identifierhttp://hdl.handle.net/10722/304344
ISBN
ISSN
2023 SCImago Journal Rankings: 0.152
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorGe, Z-
dc.contributor.authorSong, L-
dc.contributor.authorLam, EYM-
dc.date.accessioned2021-09-23T08:58:44Z-
dc.date.available2021-09-23T08:58:44Z-
dc.date.issued2020-
dc.identifier.citationProceedings of SPIE, v. 11525: SPIE Future Sensing Technologies Conference, Virtual Meeting, Japan, 9-13 November 2020, paper 11525 1H-
dc.identifier.isbn9781510638617-
dc.identifier.issn0277-786X-
dc.identifier.urihttp://hdl.handle.net/10722/304344-
dc.description.abstractLight field (LF) imaging provides rich spatial and angular information, but is problematic in low-light environment as the images suffer from low contrast and visibility. In this paper, we present a learning-based method to enhance low-light LF images. A high-dimensional convolutional neural network (CNN) is introduced to extract the spatio-angular features from the LF. The network operates directly on the four-dimensional LF data rather than on individual sub-aperture images, avoiding the loss of geometric information. Color compensation is then performed on the enhanced LF images coming from the high-dimensional CNN to reduce color distortion. The experimental results show that the proposed method achieves noticeable improvement compared with state-of-the-art low-light image restoration techniques in both visual inspection and objective assessments.-
dc.languageeng-
dc.publisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml?WT.svl=mddp2-
dc.relation.ispartofProceedings of SPIE, v. 11525: SPIE Future Sensing Technologies Conference-
dc.rightsSPIE - International Society for Optical Engineering. Proceedings. Copyright © SPIE - International Society for Optical Engineering.-
dc.titleLight field image restoration in low-light environment-
dc.typeConference_Paper-
dc.identifier.emailLam, EYM: elam@eee.hku.hk-
dc.identifier.authorityLam, EYM=rp00131-
dc.identifier.doi10.1117/12.2580033-
dc.identifier.scopuseid_2-s2.0-85097143608-
dc.identifier.hkuros325005-
dc.identifier.volume11525-
dc.identifier.spage11525 1H-
dc.identifier.epage11525 1H-
dc.identifier.isiWOS:000649367600040-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats