Antipodally invariant metrics for fast regression-based super-resolution

Dictionary-based super-resolution (SR) algorithms usually select dictionary atoms based on the distance or similarity metrics. Although the optimal selection of the nearest neighbors is of central importance for such methods, the impact of using proper metrics for SR has been overlooked in literatur...

Descripción completa

Detalles Bibliográficos
Autores: Pérez-Pellitero, Eduardo, Salvador, Jordi, Ruiz Hidalgo, Javier|||0000-0001-6774-685X, Rosenhahn, Bodo
Tipo de recurso: artículo
Fecha de publicación:2016
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/89049
Acceso en línea:https://hdl.handle.net/2117/89049
https://dx.doi.org/10.1109/TIP.2016.2549362
Access Level:acceso abierto
Palabra clave:Image processing -- Digital techniques
Antipodes
Regression
Spherical Hashing
Super-Resolution
Super-resolution
Spherical hashing
Imatges -- Processament -- Tècniques digitals
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
id ES_279a67fc32721a0ec00290b3ed0a3193
oai_identifier_str oai:upcommons.upc.edu:2117/89049
network_acronym_str ES
network_name_str España
repository_id_str
spelling Antipodally invariant metrics for fast regression-based super-resolutionPérez-Pellitero, EduardoSalvador, JordiRuiz Hidalgo, Javier|||0000-0001-6774-685XRosenhahn, BodoImage processing -- Digital techniquesAntipodesRegressionSpherical HashingSuper-ResolutionSuper-resolutionAntipodesRegressionSpherical hashingImatges -- Processament -- Tècniques digitalsÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeoDictionary-based super-resolution (SR) algorithms usually select dictionary atoms based on the distance or similarity metrics. Although the optimal selection of the nearest neighbors is of central importance for such methods, the impact of using proper metrics for SR has been overlooked in literature, mainly due to the vast usage of Euclidean distance. In this paper, we present a very fast regression-based algorithm, which builds on the densely populated anchored neighborhoods and sublinear search structures. We perform a study of the nature of the features commonly used for SR, observing that those features usually lie in the unitary hypersphere, where every point has a diametrically opposite one, i.e., its antipode, with same module and angle, but the opposite direction. Even though, we validate the benefits of using antipodally invariant metrics, most of the binary splits use Euclidean distance, which does not handle antipodes optimally. In order to benefit from both the worlds, we propose a simple yet effective antipodally invariant transform that can be easily included in the Euclidean distance calculation. We modify the original spherical hashing algorithm with this metric in our antipodally invariant spherical hashing scheme, obtaining the same performance as a pure antipodally invariant metric. We round up our contributions with a novel feature transform that obtains a better coarse approximation of the input image thanks to iterative backprojection. The performance of our method, which we named antipodally invariant SR, improves quality (Peak Signal to Noise Ratio) and it is faster than any other state-of-the-art method.Peer Reviewed20162016-03-3120162016-07-21journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/89049https://dx.doi.org/10.1109/TIP.2016.2549362reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2http://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/890492026-05-27T15:37:01Z
dc.title.none.fl_str_mv Antipodally invariant metrics for fast regression-based super-resolution
title Antipodally invariant metrics for fast regression-based super-resolution
spellingShingle Antipodally invariant metrics for fast regression-based super-resolution
Pérez-Pellitero, Eduardo
Image processing -- Digital techniques
Antipodes
Regression
Spherical Hashing
Super-Resolution
Super-resolution
Antipodes
Regression
Spherical hashing
Imatges -- Processament -- Tècniques digitals
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
title_short Antipodally invariant metrics for fast regression-based super-resolution
title_full Antipodally invariant metrics for fast regression-based super-resolution
title_fullStr Antipodally invariant metrics for fast regression-based super-resolution
title_full_unstemmed Antipodally invariant metrics for fast regression-based super-resolution
title_sort Antipodally invariant metrics for fast regression-based super-resolution
dc.creator.none.fl_str_mv Pérez-Pellitero, Eduardo
Salvador, Jordi
Ruiz Hidalgo, Javier|||0000-0001-6774-685X
Rosenhahn, Bodo
author Pérez-Pellitero, Eduardo
author_facet Pérez-Pellitero, Eduardo
Salvador, Jordi
Ruiz Hidalgo, Javier|||0000-0001-6774-685X
Rosenhahn, Bodo
author_role author
author2 Salvador, Jordi
Ruiz Hidalgo, Javier|||0000-0001-6774-685X
Rosenhahn, Bodo
author2_role author
author
author
dc.subject.none.fl_str_mv Image processing -- Digital techniques
Antipodes
Regression
Spherical Hashing
Super-Resolution
Super-resolution
Antipodes
Regression
Spherical hashing
Imatges -- Processament -- Tècniques digitals
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
topic Image processing -- Digital techniques
Antipodes
Regression
Spherical Hashing
Super-Resolution
Super-resolution
Antipodes
Regression
Spherical hashing
Imatges -- Processament -- Tècniques digitals
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
description Dictionary-based super-resolution (SR) algorithms usually select dictionary atoms based on the distance or similarity metrics. Although the optimal selection of the nearest neighbors is of central importance for such methods, the impact of using proper metrics for SR has been overlooked in literature, mainly due to the vast usage of Euclidean distance. In this paper, we present a very fast regression-based algorithm, which builds on the densely populated anchored neighborhoods and sublinear search structures. We perform a study of the nature of the features commonly used for SR, observing that those features usually lie in the unitary hypersphere, where every point has a diametrically opposite one, i.e., its antipode, with same module and angle, but the opposite direction. Even though, we validate the benefits of using antipodally invariant metrics, most of the binary splits use Euclidean distance, which does not handle antipodes optimally. In order to benefit from both the worlds, we propose a simple yet effective antipodally invariant transform that can be easily included in the Euclidean distance calculation. We modify the original spherical hashing algorithm with this metric in our antipodally invariant spherical hashing scheme, obtaining the same performance as a pure antipodally invariant metric. We round up our contributions with a novel feature transform that obtains a better coarse approximation of the input image thanks to iterative backprojection. The performance of our method, which we named antipodally invariant SR, improves quality (Peak Signal to Noise Ratio) and it is faster than any other state-of-the-art method.
publishDate 2016
dc.date.none.fl_str_mv 2016
2016-03-31
2016
2016-07-21
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/89049
https://dx.doi.org/10.1109/TIP.2016.2549362
url https://hdl.handle.net/2117/89049
https://dx.doi.org/10.1109/TIP.2016.2549362
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404896700137472
score 15,300719

Similares en LA Referencia