File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TIP.2021.3066293
- Scopus: eid_2-s2.0-85103247695
- PMID: 33750690
- WOS: WOS:000634491000009
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Light Field View Synthesis via Aperture Disparity and Warping Confidence Map
Title | Light Field View Synthesis via Aperture Disparity and Warping Confidence Map |
---|---|
Authors | |
Keywords | View synthesis image-based rendering light field aperture flow epipolar property |
Issue Date | 2021 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83 |
Citation | IEEE Transactions on Image Processing, 2021, v. 30, p. 3908-3921 How to Cite? |
Abstract | This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from different input images may not be consistent due to obstruction in the light path. We overcome this by jointly modeling the epipolar property and occlusion in designing a convolutional neural network. We start by defining and computing the aperture disparity map, which approximates the parallax and measures the pixel-wise shift between two views. While this relates to free-space rendering and can fail near the object boundaries, we further develop a warping confidence map to address pixel occlusion in these challenging regions. The proposed method is evaluated on diverse real-world and synthetic light field scenes, and it shows better performance over several state-of-the-art techniques. |
Persistent Identifier | http://hdl.handle.net/10722/304222 |
ISSN | 2021 Impact Factor: 11.041 2020 SCImago Journal Rankings: 1.778 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | MENG, N | - |
dc.contributor.author | Li, K | - |
dc.contributor.author | Liu, J | - |
dc.contributor.author | Lam, EY | - |
dc.date.accessioned | 2021-09-23T08:56:58Z | - |
dc.date.available | 2021-09-23T08:56:58Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Image Processing, 2021, v. 30, p. 3908-3921 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304222 | - |
dc.description.abstract | This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from different input images may not be consistent due to obstruction in the light path. We overcome this by jointly modeling the epipolar property and occlusion in designing a convolutional neural network. We start by defining and computing the aperture disparity map, which approximates the parallax and measures the pixel-wise shift between two views. While this relates to free-space rendering and can fail near the object boundaries, we further develop a warping confidence map to address pixel occlusion in these challenging regions. The proposed method is evaluated on diverse real-world and synthetic light field scenes, and it shows better performance over several state-of-the-art techniques. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83 | - |
dc.relation.ispartof | IEEE Transactions on Image Processing | - |
dc.rights | IEEE Transactions on Image Processing. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©20xx 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 | View synthesis | - |
dc.subject | image-based rendering | - |
dc.subject | light field | - |
dc.subject | aperture flow | - |
dc.subject | epipolar property | - |
dc.title | Light Field View Synthesis via Aperture Disparity and Warping Confidence Map | - |
dc.type | Article | - |
dc.identifier.email | Lam, EY: elam@eee.hku.hk | - |
dc.identifier.authority | Lam, EY=rp00131 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TIP.2021.3066293 | - |
dc.identifier.pmid | 33750690 | - |
dc.identifier.scopus | eid_2-s2.0-85103247695 | - |
dc.identifier.hkuros | 324990 | - |
dc.identifier.volume | 30 | - |
dc.identifier.spage | 3908 | - |
dc.identifier.epage | 3921 | - |
dc.identifier.isi | WOS:000634491000009 | - |
dc.publisher.place | United States | - |