File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICIP.2019.8803480
- Scopus: eid_2-s2.0-85076818682
- WOS: WOS:000521828604149
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Spatial and Angular Reconstruction of Light Field Based on Deep Generative Networks
Title | Spatial and Angular Reconstruction of Light Field Based on Deep Generative Networks |
---|---|
Authors | |
Keywords | Light field reconstruction generative adversarial networks computational imaging high-dimensional convolution deep learning |
Issue Date | 2019 |
Publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349 |
Citation | 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 22-25 September 2019, p. 4659-4663 How to Cite? |
Abstract | Light field (LF) cameras often have significant limitations in spatial and angular resolutions due to their design. Many techniques that attempt to reconstruct LF images at a higher resolution only consider either spatial or angular resolution, but not both. We propose a generative network using high-dimensional convolution to improve both aspects. Our experimental results on both synthetic and real-world data demonstrate that the proposed model outperforms existing state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and visual quality. The proposed method can also generate more realistic spatial details with better fidelity. |
Persistent Identifier | http://hdl.handle.net/10722/288222 |
ISSN | 2020 SCImago Journal Rankings: 0.315 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Meng, N | - |
dc.contributor.author | Zeng, T | - |
dc.contributor.author | Lam, EYM | - |
dc.date.accessioned | 2020-10-05T12:09:41Z | - |
dc.date.available | 2020-10-05T12:09:41Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 22-25 September 2019, p. 4659-4663 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288222 | - |
dc.description.abstract | Light field (LF) cameras often have significant limitations in spatial and angular resolutions due to their design. Many techniques that attempt to reconstruct LF images at a higher resolution only consider either spatial or angular resolution, but not both. We propose a generative network using high-dimensional convolution to improve both aspects. Our experimental results on both synthetic and real-world data demonstrate that the proposed model outperforms existing state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and visual quality. The proposed method can also generate more realistic spatial details with better fidelity. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349 | - |
dc.relation.ispartof | International Conference on Image Processing Proceedings | - |
dc.rights | International Conference on Image Processing Proceedings. Copyright © IEEE. | - |
dc.rights | ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Light field reconstruction | - |
dc.subject | generative adversarial networks | - |
dc.subject | computational imaging | - |
dc.subject | high-dimensional convolution | - |
dc.subject | deep learning | - |
dc.title | Spatial and Angular Reconstruction of Light Field Based on Deep Generative Networks | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Lam, EYM: elam@eee.hku.hk | - |
dc.identifier.authority | Lam, EYM=rp00131 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1109/ICIP.2019.8803480 | - |
dc.identifier.scopus | eid_2-s2.0-85076818682 | - |
dc.identifier.hkuros | 314918 | - |
dc.identifier.spage | 4659 | - |
dc.identifier.epage | 4663 | - |
dc.identifier.isi | WOS:000521828604149 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1522-4880 | - |