File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ACCESS.2019.2900153
- Scopus: eid_2-s2.0-85062733685
- WOS: WOS:000461249700001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Computational Light Field Generation Using Deep Nonparametric Bayesian Learning
Title | Computational Light Field Generation Using Deep Nonparametric Bayesian Learning |
---|---|
Authors | |
Keywords | Convolutional neural network Deep learning Image reconstruction Light field imaging Nonparametric Bayesian |
Issue Date | 2019 |
Publisher | Institute of Electrical and Electronics Engineers: Open Access Journals. 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? |
Abstract | In 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 Identifier | http://hdl.handle.net/10722/275026 |
ISSN | 2023 Impact Factor: 3.4 2023 SCImago Journal Rankings: 0.960 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Meng, N | - |
dc.contributor.author | Sun, X | - |
dc.contributor.author | So, HKH | - |
dc.contributor.author | Lam, EY | - |
dc.date.accessioned | 2019-09-10T02:33:56Z | - |
dc.date.available | 2019-09-10T02:33:56Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | IEEE Access, 2019, v. 7, p. 24990-25000 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | http://hdl.handle.net/10722/275026 | - |
dc.description.abstract | In 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.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers: Open Access Journals. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6287639 | - |
dc.relation.ispartof | IEEE 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.subject | Convolutional neural network | - |
dc.subject | Deep learning | - |
dc.subject | Image reconstruction | - |
dc.subject | Light field imaging | - |
dc.subject | Nonparametric Bayesian | - |
dc.title | Computational Light Field Generation Using Deep Nonparametric Bayesian Learning | - |
dc.type | Article | - |
dc.identifier.email | So, HKH: hso@eee.hku.hk | - |
dc.identifier.email | Lam, EY: elam@eee.hku.hk | - |
dc.identifier.authority | So, HKH=rp00169 | - |
dc.identifier.authority | Lam, EY=rp00131 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1109/ACCESS.2019.2900153 | - |
dc.identifier.scopus | eid_2-s2.0-85062733685 | - |
dc.identifier.hkuros | 304141 | - |
dc.identifier.volume | 7 | - |
dc.identifier.spage | 24990 | - |
dc.identifier.epage | 25000 | - |
dc.identifier.isi | WOS:000461249700001 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 2169-3536 | - |