File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Perceptual loss for light field reconstruction in high-dimensional convolutional neural networks

TitlePerceptual loss for light field reconstruction in high-dimensional convolutional neural networks
Authors
Issue Date2019
Citation
Optics InfoBase Conference Papers, 2019, v. Part F170-COSI 2019 How to Cite?
AbstractWe explore the benefits of perceptual loss for light field (LF) spatial reconstruction in a high-dimensional convolutional neural network. The results outperform some state-of-the-art methods for LF or image super-resolution.
Persistent Identifierhttp://hdl.handle.net/10722/330421

 

DC FieldValueLanguage
dc.contributor.authorMeng, Nan-
dc.contributor.authorZeng, Tianjiao-
dc.contributor.authorLam, Edmund Y.-
dc.date.accessioned2023-09-05T12:10:27Z-
dc.date.available2023-09-05T12:10:27Z-
dc.date.issued2019-
dc.identifier.citationOptics InfoBase Conference Papers, 2019, v. Part F170-COSI 2019-
dc.identifier.urihttp://hdl.handle.net/10722/330421-
dc.description.abstractWe explore the benefits of perceptual loss for light field (LF) spatial reconstruction in a high-dimensional convolutional neural network. The results outperform some state-of-the-art methods for LF or image super-resolution.-
dc.languageeng-
dc.relation.ispartofOptics InfoBase Conference Papers-
dc.titlePerceptual loss for light field reconstruction in high-dimensional convolutional neural networks-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1364/COSI.2019.CM1A.CW1A.5-
dc.identifier.scopuseid_2-s2.0-85089918270-
dc.identifier.volumePart F170-COSI 2019-
dc.identifier.eissn2162-2701-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats