Image Zoom Completion
HIDANE, Moncef
Institut National des Sciences Appliquées - Centre Val de Loire [INSA CVL]
Laboratoire d'Informatique Fondamentale et Appliquée de Tours [LIFAT]
Institut National des Sciences Appliquées - Centre Val de Loire [INSA CVL]
Laboratoire d'Informatique Fondamentale et Appliquée de Tours [LIFAT]
EL GHECHE, Mireille
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire de l'intégration, du matériau au système [IMS]
See more >
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire de l'intégration, du matériau au système [IMS]
HIDANE, Moncef
Institut National des Sciences Appliquées - Centre Val de Loire [INSA CVL]
Laboratoire d'Informatique Fondamentale et Appliquée de Tours [LIFAT]
Institut National des Sciences Appliquées - Centre Val de Loire [INSA CVL]
Laboratoire d'Informatique Fondamentale et Appliquée de Tours [LIFAT]
EL GHECHE, Mireille
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire de l'intégration, du matériau au système [IMS]
< Reduce
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire de l'intégration, du matériau au système [IMS]
Language
en
Article de revue
This item was published in
IEEE Transactions on Image Processing. 2016-08-01, vol. 25, n° 8, p. 3505-3517
Institute of Electrical and Electronics Engineers
English Abstract
We consider the problem of recovering a high-resolution image from a pair consisting of a complete low-resolution image and a high-resolution but incomplete one. We refer to this task as the image zoom completion (IZC) ...Read more >
We consider the problem of recovering a high-resolution image from a pair consisting of a complete low-resolution image and a high-resolution but incomplete one. We refer to this task as the image zoom completion (IZC) problem. After discussing possible contexts in which this setting may arise, we study three regularization strategies, giving full details concerning the numerical optimization of the corresponding energies, and discussing the benefits and shortcomings of each method. As the application that leads us to consider the IZC setting concerns images with strong textural content, we evaluate the performance of the proposed methods on a set of Brodatz textures, comparing the results we get with those obtained with two recent state-of-the-art single-image super-resolution algorithms.Read less <
English Keywords
low-rank
nonlocal
graph laplacian
super-resolution
total variation
optimization
Douglas-Rachford
nuclear norm
Origin
Hal imported