File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: LightGAN: A Deep Generative Model for Light Field Reconstruction

TitleLightGAN: A Deep Generative Model for Light Field Reconstruction
Authors
KeywordsImage reconstruction
Convolution
Spatial resolution
Correlation
Generators
Issue Date2020
PublisherInstitute of Electrical and Electronics Engineers (IEEE): OAJ. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6287639
Citation
IEEE Access, 2020, v. 8, p. 116052-116063 How to Cite?
AbstractA light field image captured by a plenoptic camera can be considered a sampling of light distribution within a given space. However, with the limited pixel count of the sensor, the acquisition of a high-resolution sample often comes at the expense of losing parallax information. In this work, we present a learning-based generative framework to overcome such tradeoff by directly simulating the light field distribution. An important module of our model is the high-dimensional residual block, which fully exploits the spatio-angular information. By directly learning the distribution, our approach can generate both high-quality sub-aperture images and densely-sampled light fields. Experimental results on both real-world and synthetic datasets demonstrate that the proposed method outperforms other state-of-the-art approaches and achieves visually more realistic results.
Persistent Identifierhttp://hdl.handle.net/10722/287937
ISSN
2019 Impact Factor: 3.745
2015 SCImago Journal Rankings: 0.947

 

DC FieldValueLanguage
dc.contributor.authorMENG, N-
dc.contributor.authorGE, Z-
dc.contributor.authorZENG, T-
dc.contributor.authorLam, EY-
dc.date.accessioned2020-10-05T12:05:26Z-
dc.date.available2020-10-05T12:05:26Z-
dc.date.issued2020-
dc.identifier.citationIEEE Access, 2020, v. 8, p. 116052-116063-
dc.identifier.issn2169-3536-
dc.identifier.urihttp://hdl.handle.net/10722/287937-
dc.description.abstractA light field image captured by a plenoptic camera can be considered a sampling of light distribution within a given space. However, with the limited pixel count of the sensor, the acquisition of a high-resolution sample often comes at the expense of losing parallax information. In this work, we present a learning-based generative framework to overcome such tradeoff by directly simulating the light field distribution. An important module of our model is the high-dimensional residual block, which fully exploits the spatio-angular information. By directly learning the distribution, our approach can generate both high-quality sub-aperture images and densely-sampled light fields. Experimental results on both real-world and synthetic datasets demonstrate that the proposed method outperforms other state-of-the-art approaches and achieves visually more realistic results.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE): OAJ. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6287639-
dc.relation.ispartofIEEE Access-
dc.rightsIEEE Access. Copyright © Institute of Electrical and Electronics Engineers (IEEE): OAJ.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectImage reconstruction-
dc.subjectConvolution-
dc.subjectSpatial resolution-
dc.subjectCorrelation-
dc.subjectGenerators-
dc.titleLightGAN: A Deep Generative Model for Light Field Reconstruction-
dc.typeArticle-
dc.identifier.emailLam, EY: elam@eee.hku.hk-
dc.identifier.authorityLam, EY=rp00131-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ACCESS.2020.3004477-
dc.identifier.scopuseid_2-s2.0-85087828833-
dc.identifier.hkuros314917-
dc.identifier.volume8-
dc.identifier.spage116052-
dc.identifier.epage116063-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats