Show simple item record

dc.contributor.authorPérez-Pellitero, Eduardo
dc.contributor.authorSalvador, Jordi
dc.contributor.authorTorres-Xirau, Iban
dc.contributor.authorRuiz Hidalgo, Javier
dc.contributor.authorRosenhahn, Bodo
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2015-04-22T15:43:32Z
dc.date.available2016-04-22T00:30:59Z
dc.date.created2014-11-01
dc.date.issued2014-11-01
dc.identifier.citationPérez-Pellitero, E. [et al.]. Fast super-resolution via dense local training and inverse regressor search. "Lecture notes in computer science", 01 Novembre 2014, p. 346-359.
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/2117/27529
dc.description.abstractRegression-based Super-Resolution (SR) addresses the upscaling problem by learning a mapping function (i.e. regressor) from the low-resolution to the high-resolution manifold. Under the locally linear assumption, this complex non-linear mapping can be properly modeled by a set of linear regressors distributed across the manifold. In such methods, most of the testing time is spent searching for the right regressor within this trained set. In this paper we propose a novel inverse-search approach for regression-based SR. Instead of performing a search from the image to the dictionary of regressors, the search is done inversely from the regressors’ dictionary to the image patches. We approximate this framework by applying spherical hashing to both image and regressors, which reduces the inverse search into computing a trained function. Additionally, we propose an improved training scheme for SR linear regressors which improves perceived and objective quality. By merging both contributions we improve speed and quality compared to the state-of-the-art.
dc.format.extent14 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subjectÀrees temàtiques de la UPC::So, imatge i multimèdia::Creació multimèdia::Imatge digital
dc.subject.lcshComputer vision
dc.subject.lcshImage processing
dc.titleFast super-resolution via dense local training and inverse regressor search
dc.typeArticle
dc.subject.lemacVisió per ordinador
dc.subject.lemacImatges -- Processament
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1007/978-3-319-16811-1_23
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://link.springer.com/chapter/10.1007%2F978-3-319-16811-1_23
dc.rights.accessOpen Access
drac.iddocument15539390
dc.description.versionPostprint (author's final draft)
upcommons.citation.authorPérez-Pellitero, E.; Salvador, J.; Torres-Xirau, I.; Ruiz-Hidalgo, J.; Rosenhahn, B.
upcommons.citation.publishedtrue
upcommons.citation.publicationNameLecture notes in computer science
upcommons.citation.startingPage346
upcommons.citation.endingPage359


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder