Angular‐flexible network for light field image super‐resolution

Abstract Light field (LF) cameras capture scenes from multiple views and provide additional angular information for image super‐resolution (SR). Existing CNN‐based LF image SR methods commonly develop specific models for different angular resolutions. However, since the angular resolution can vary s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhengyu Liang, Yingqian Wang, Longguang Wang, Jungang Yang, Shilin Zhou
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/a9ce25c0a3e842f4891f015e69df83c9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a9ce25c0a3e842f4891f015e69df83c9
record_format	dspace
spelling	oai:doaj.org-article:a9ce25c0a3e842f4891f015e69df83c92021-11-19T05:42:54ZAngular‐flexible network for light field image super‐resolution1350-911X0013-519410.1049/ell2.12312https://doaj.org/article/a9ce25c0a3e842f4891f015e69df83c92021-11-01T00:00:00Zhttps://doi.org/10.1049/ell2.12312https://doaj.org/toc/0013-5194https://doaj.org/toc/1350-911XAbstract Light field (LF) cameras capture scenes from multiple views and provide additional angular information for image super‐resolution (SR). Existing CNN‐based LF image SR methods commonly develop specific models for different angular resolutions. However, since the angular resolution can vary significantly with different LF devices, these methods have limited flexibility for real‐world applications. Here, an angular‐flexible network to use a single model to super‐resolve LF images of arbitrary angular resolution is proposed. In this method, spatial and angular feature extractors are designed to achieve angular‐flexible feature extraction, and develop a decouple‐and‐fuse module for SR reconstruction. Moreover, a mixed‐angular‐resolution training strategy is proposed to further enhance the angular flexibility. Experimental results on five public datasets demonstrate the state‐of‐the‐art performance of the method. Source codes are available at https://github.com/ZhengyuLiang24/LF‐AFnet. Here, an angular‐flexible network for light field image super‐resolution is proposed. The network can handle LFs captured by different kinds of devices with arbitrary angular resolutions. Experimental results demonstrate the effectiveness and superior performance of the method.Zhengyu LiangYingqian WangLongguang WangJungang YangShilin ZhouWileyarticleElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENElectronics Letters, Vol 57, Iss 24, Pp 921-924 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electrical engineering. Electronics. Nuclear engineering TK1-9971 Zhengyu Liang Yingqian Wang Longguang Wang Jungang Yang Shilin Zhou Angular‐flexible network for light field image super‐resolution
description	Abstract Light field (LF) cameras capture scenes from multiple views and provide additional angular information for image super‐resolution (SR). Existing CNN‐based LF image SR methods commonly develop specific models for different angular resolutions. However, since the angular resolution can vary significantly with different LF devices, these methods have limited flexibility for real‐world applications. Here, an angular‐flexible network to use a single model to super‐resolve LF images of arbitrary angular resolution is proposed. In this method, spatial and angular feature extractors are designed to achieve angular‐flexible feature extraction, and develop a decouple‐and‐fuse module for SR reconstruction. Moreover, a mixed‐angular‐resolution training strategy is proposed to further enhance the angular flexibility. Experimental results on five public datasets demonstrate the state‐of‐the‐art performance of the method. Source codes are available at https://github.com/ZhengyuLiang24/LF‐AFnet. Here, an angular‐flexible network for light field image super‐resolution is proposed. The network can handle LFs captured by different kinds of devices with arbitrary angular resolutions. Experimental results demonstrate the effectiveness and superior performance of the method.
format	article
author	Zhengyu Liang Yingqian Wang Longguang Wang Jungang Yang Shilin Zhou
author_facet	Zhengyu Liang Yingqian Wang Longguang Wang Jungang Yang Shilin Zhou
author_sort	Zhengyu Liang
title	Angular‐flexible network for light field image super‐resolution
title_short	Angular‐flexible network for light field image super‐resolution
title_full	Angular‐flexible network for light field image super‐resolution
title_fullStr	Angular‐flexible network for light field image super‐resolution
title_full_unstemmed	Angular‐flexible network for light field image super‐resolution
title_sort	angular‐flexible network for light field image super‐resolution
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/a9ce25c0a3e842f4891f015e69df83c9
work_keys_str_mv	AT zhengyuliang angularflexiblenetworkforlightfieldimagesuperresolution AT yingqianwang angularflexiblenetworkforlightfieldimagesuperresolution AT longguangwang angularflexiblenetworkforlightfieldimagesuperresolution AT jungangyang angularflexiblenetworkforlightfieldimagesuperresolution AT shilinzhou angularflexiblenetworkforlightfieldimagesuperresolution
_version_	1718420393735225344

Angular‐flexible network for light field image super‐resolution

Ejemplares similares