File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Computational Light Field Generation Using Deep Nonparametric Bayesian Learning

TitleComputational Light Field Generation Using Deep Nonparametric Bayesian Learning
Authors
KeywordsConvolutional neural network
Deep learning
Image reconstruction
Light field imaging
Nonparametric Bayesian
Issue Date2019
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, 2019, v. 7, p. 24990-25000 How to Cite?
AbstractIn this paper, we present a deep nonparametric Bayesian method to synthesize a light field from a single image. Conventionally, light-field capture requires special optical architecture, and the gain in angular resolution often comes at the expense of a reduction in spatial resolution. Techniques for computationally generating the light field from a single image can be expanded further to a variety of applications, ranging from microscopy and materials analysis to vision-based robotic control and autonomous vehicles. We treat the light field as multiple sub-aperture views, and to compute the novel viewpoints, our model contains three major components. First, a convolutional neural network is used for predicting the depth probability map from the image. Second, a multi-scale feature dictionary is constructed within a multi-layer dictionary learning network. Third, the novel views are synthesized taking into account both the probabilistic depth map and the multi-scale feature dictionary. The experiments show that our method outperforms several state-of-the-art novel view synthesis methods in delivering good image resolution.
Persistent Identifierhttp://hdl.handle.net/10722/275026
ISSN
2019 Impact Factor: 3.745
2015 SCImago Journal Rankings: 0.947
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorMeng, N-
dc.contributor.authorSun, X-
dc.contributor.authorSo, HKH-
dc.contributor.authorLam, EY-
dc.date.accessioned2019-09-10T02:33:56Z-
dc.date.available2019-09-10T02:33:56Z-
dc.date.issued2019-
dc.identifier.citationIEEE Access, 2019, v. 7, p. 24990-25000-
dc.identifier.issn2169-3536-
dc.identifier.urihttp://hdl.handle.net/10722/275026-
dc.description.abstractIn this paper, we present a deep nonparametric Bayesian method to synthesize a light field from a single image. Conventionally, light-field capture requires special optical architecture, and the gain in angular resolution often comes at the expense of a reduction in spatial resolution. Techniques for computationally generating the light field from a single image can be expanded further to a variety of applications, ranging from microscopy and materials analysis to vision-based robotic control and autonomous vehicles. We treat the light field as multiple sub-aperture views, and to compute the novel viewpoints, our model contains three major components. First, a convolutional neural network is used for predicting the depth probability map from the image. Second, a multi-scale feature dictionary is constructed within a multi-layer dictionary learning network. Third, the novel views are synthesized taking into account both the probabilistic depth map and the multi-scale feature dictionary. The experiments show that our method outperforms several state-of-the-art novel view synthesis methods in delivering good image resolution.-
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.rights© 2019 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.-
dc.subjectConvolutional neural network-
dc.subjectDeep learning-
dc.subjectImage reconstruction-
dc.subjectLight field imaging-
dc.subjectNonparametric Bayesian-
dc.titleComputational Light Field Generation Using Deep Nonparametric Bayesian Learning-
dc.typeArticle-
dc.identifier.emailSo, HKH: hso@eee.hku.hk-
dc.identifier.emailLam, EY: elam@eee.hku.hk-
dc.identifier.authoritySo, HKH=rp00169-
dc.identifier.authorityLam, EY=rp00131-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ACCESS.2019.2900153-
dc.identifier.scopuseid_2-s2.0-85062733685-
dc.identifier.hkuros304141-
dc.identifier.volume7-
dc.identifier.spage24990-
dc.identifier.epage25000-
dc.identifier.isiWOS:000461249700001-
dc.publisher.placeUnited States-
dc.identifier.issnl2169-3536-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats