eprintid: 2417
rev_number: 5
eprint_status: archive
userid: 6
dir: disk0/00/00/24/17
datestamp: 2014-12-11 11:38:40
lastmod: 2014-12-11 11:38:40
status_changed: 2014-12-11 11:38:40
type: article
metadata_visibility: show
creators_name: Bevilacqua, Marco
creators_name: Roumy, Aline
creators_name: Guillemot, Christine
creators_name: Alberi-Morel, Marie Line
creators_id: marco.bevilacqua@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
title: Single-image super-resolution via linear mapping of interpolated self-examples
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: Super resolution; example-based; neighbor embedding; regression; super resolution

abstract: This paper presents a novel example-based single-image superresolution procedure that upscales to high-resolution (HR) a given low-resolution (LR) input image without relying on an external dictionary of image examples. The dictionary instead is built from the LR input image itself, by generating a double pyramid of recursively scaled, and subsequently interpolated, images, from which self-examples are extracted. The upscaling procedure is multipass, i.e., the output image is constructed by means of gradual increases, and consists in learning special linear mapping functions on this double pyramid, as many as the number of patches in the current image to upscale. More precisely, for each LR patch, similar self-examples are found, and, because of them, a linear function is learned to directly map it into its HR version. Iterative back projection is also employed to ensure consistency at each pass of the procedure. Extensive experiments and comparisons with other state-of-the-art methods, based both on external and internal dictionaries, show that our algorithm can produce visually pleasant upscalings, with sharp edges and well reconstructed details. Moreover, when considering objective metrics, such as Peak signal-to-noise ratio and Structural similarity, our method turns out to give the best performance.
date: 2014-12
date_type: published
publication: IEEE Transactions on image processing
volume: 23
number: 12
publisher: IEEE
pagerange: 5334-5347
id_number: 10.1109/TIP.2014.2364116
refereed: TRUE
issn: 1057-7149
official_url: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6930774&isnumber=6924847
citation:   Bevilacqua, Marco and Roumy, Aline and Guillemot, Christine and Alberi-Morel, Marie Line  Single-image super-resolution via linear mapping of interpolated self-examples.  IEEE Transactions on image processing, 23 (12).  pp. 5334-5347.  ISSN 1057-7149      (2014)