Joint learning for single-image super-resolution via a coupled constraint

Gao, X; Zhang, K; Tao, D; Li, X

Joint learning for single-image super-resolution via a coupled constraint

Gao, X Zhang, K Tao, D

Li, X

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Image Processing, 2012, 21 (2), pp. 469 - 480
Issue Date:: 2012-02-01

Closed Access

	Filename	Description	Size
	2011005495OK.pdf		1.32 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Gao, X	en_US
dc.contributor.author	Zhang, K	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Li, X	en_US
dc.date.issued	2012-02-01	en_US
dc.identifier.citation	IEEE Transactions on Image Processing, 2012, 21 (2), pp. 469 - 480	en_US
dc.identifier.issn	1057-7149	en_US
dc.identifier.uri	http://hdl.handle.net/10453/22225
dc.description.abstract	The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k-nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR-HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines. © 2011 IEEE.	en_US
dc.relation.ispartof	IEEE Transactions on Image Processing	en_US
dc.relation.isbasedon	10.1109/TIP.2011.2161482	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Joint learning for single-image super-resolution via a coupled constraint	en_US
dc.type	Journal Article
utslib.citation.volume	2	en_US
utslib.citation.volume	21	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1702 Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	2	en_US
pubs.publication-status	Published	en_US
pubs.volume	21	en_US

Abstract:

The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k-nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR-HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines. © 2011 IEEE.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/22225