Light Field Image Coding using High Order Prediction Training

Monteiro, Ricardo J. S.; Nunes, Paulo J. L.; Faria, Sergio; M. M. Rodrigues, Nuno

Publication

Light Field Image Coding using High Order Prediction Training

2018-09Conference paper

dc.contributor.author	Monteiro, Ricardo J. S.
dc.contributor.author	Nunes, Paulo J. L.
dc.contributor.author	Faria, Sergio
dc.contributor.author	M. M. Rodrigues, Nuno
dc.date.accessioned	2025-06-02T14:08:38Z
dc.date.available	2025-06-02T14:08:38Z
dc.date.issued	2018-09
dc.description.abstract	This paper proposes a new method for light field image coding relying on a high order prediction mode based on a training algorithm. The proposed approach is applied as an Intra prediction method based on a two-stage block-wise high order prediction model that supports geometric transformations up to eight degrees of freedom. Light field images comprise an array of micro-images that are related by complex perspective deformations that cannot be efficiently compensated by state-of-the-art image coding techniques, which are usually based on low order translational prediction models. The proposed prediction mode is able to exploit the non-local spatial redundancy introduced by light field image structure and a training algorithm is applied on different micro-images that are available in the reference region aiming at reducing the amount of signaling data sent to the receiver. The training direction that generates the most efficient geometric transformation for the current block is determined in the encoder side and signaled to the decoder using an index. The decoder is therefore able to repeat the high order prediction training to generate the desired geometric transformation. Experimental results show bitrate savings up to 12.57% and 50.03% relatively to a light field image coding solution based on low order prediction without training and HEVC, respectively.	por
dc.identifier.doi	10.23919/eusipco.2018.8553150
dc.identifier.isbn	978-9-0827-9701-5
dc.identifier.issn	2076-1465
dc.identifier.uri	http://hdl.handle.net/10400.8/13060
dc.language.iso	eng
dc.peerreviewed	yes
dc.publisher	IEEE
dc.relation.ispartof	2018 26th European Signal Processing Conference (EUSIPCO)
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/
dc.subject	Light field image coding
dc.subject	HEVC
dc.subject	High order prediction training
dc.subject	Geometric transformations
dc.title	Light Field Image Coding using High Order Prediction Training	eng
dc.type	conference paper
dspace.entity.type	Publication
oaire.citation.conferenceDate	2018
oaire.citation.endPage	1849
oaire.citation.startPage	1845
oaire.citation.title	2018 26th European Signal Processing Conference (EUSIPCO)
oaire.version	http://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyName	Faria
person.familyName	M. M. Rodrigues
person.givenName	Sergio
person.givenName	Nuno
person.identifier.ciencia-id	8815-4101-28DD
person.identifier.ciencia-id	6917-B121-4E34
person.identifier.orcid	0000-0002-0993-9124
person.identifier.orcid	0000-0001-9536-1017
person.identifier.rid	C-5245-2011
person.identifier.scopus-author-id	14027853900
person.identifier.scopus-author-id	7006052345
relation.isAuthorOfPublication	f69bd4d6-a6ef-4d20-8148-575478909661
relation.isAuthorOfPublication	b4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isAuthorOfPublication.latestForDiscovery	f69bd4d6-a6ef-4d20-8148-575478909661