File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Example-based super-resolution with soft information and decision

TitleExample-based super-resolution with soft information and decision
Authors
KeywordsFactor graph
message passing
parametric distribution
statistical learning
super-resolution
Issue Date2013
Citation
IEEE Transactions on Multimedia, 2013, v. 15, n. 6, p. 1458-1465 How to Cite?
AbstractThe one-to-one correspondence between co-occurrence image patches of two different resolutions is extensively used in example-based super-resolution (SR). Due to the dimensionality gap between low resolution (LR) and high resolution (HR) spaces, however, an LR patch may correspond to a number of HR patches in practice. This ambiguity is difficult to be overcome with examples representing a deterministic mapping. In this paper, we propose a statistical method for exploiting the one-to-many correspondence between LR and HR patches, which we call soft information and decision. Soft information means an LR patch is mapped to a pixel-wise distribution of all its possible HR counterparts, rather than a single or a limited set of HR candidates. Relying on the soft information, example-based SR is then regarded as an optimization problem to best preserve the local consistency in the recovered HR image. This problem is solved with an efficient message passing algorithm with a factor graph model. The final decision on the HR pixel value is made upon the maximum a posteriori estimation and is called a soft decision. Experimental results demonstrate the superiority of the proposed method compared with the state-of-the-art methods, in terms of both the subjective and objective quality of synthesized HR images. © 2013 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/321525
ISSN
2023 Impact Factor: 8.4
2023 SCImago Journal Rankings: 2.260
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXiong, Zhiwei-
dc.contributor.authorXu, Dong-
dc.contributor.authorSun, Xiaoyan-
dc.contributor.authorWu, Feng-
dc.date.accessioned2022-11-03T02:19:31Z-
dc.date.available2022-11-03T02:19:31Z-
dc.date.issued2013-
dc.identifier.citationIEEE Transactions on Multimedia, 2013, v. 15, n. 6, p. 1458-1465-
dc.identifier.issn1520-9210-
dc.identifier.urihttp://hdl.handle.net/10722/321525-
dc.description.abstractThe one-to-one correspondence between co-occurrence image patches of two different resolutions is extensively used in example-based super-resolution (SR). Due to the dimensionality gap between low resolution (LR) and high resolution (HR) spaces, however, an LR patch may correspond to a number of HR patches in practice. This ambiguity is difficult to be overcome with examples representing a deterministic mapping. In this paper, we propose a statistical method for exploiting the one-to-many correspondence between LR and HR patches, which we call soft information and decision. Soft information means an LR patch is mapped to a pixel-wise distribution of all its possible HR counterparts, rather than a single or a limited set of HR candidates. Relying on the soft information, example-based SR is then regarded as an optimization problem to best preserve the local consistency in the recovered HR image. This problem is solved with an efficient message passing algorithm with a factor graph model. The final decision on the HR pixel value is made upon the maximum a posteriori estimation and is called a soft decision. Experimental results demonstrate the superiority of the proposed method compared with the state-of-the-art methods, in terms of both the subjective and objective quality of synthesized HR images. © 2013 IEEE.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Multimedia-
dc.subjectFactor graph-
dc.subjectmessage passing-
dc.subjectparametric distribution-
dc.subjectstatistical learning-
dc.subjectsuper-resolution-
dc.titleExample-based super-resolution with soft information and decision-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TMM.2013.2264654-
dc.identifier.scopuseid_2-s2.0-84884561870-
dc.identifier.volume15-
dc.identifier.issue6-
dc.identifier.spage1458-
dc.identifier.epage1465-
dc.identifier.isiWOS:000324765400020-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats