EL GHECHE, Mireille; AUJOL, Jean-François; BERTHOUMIEU, Yannick; DELEDALLE, Charles-Alban

doi:10.1109/TIP.2016.2627812

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

EL GHECHE, Mireille
Laboratoire de l'intégration, du matériau au système [IMS]

AUJOL, Jean-François
Institut de Mathématiques de Bordeaux [IMB]

BERTHOUMIEU, Yannick
Laboratoire de l'intégration, du matériau au système [IMS]

Langue

Article de revue

Ce document a été publié dans

IEEE Transactions on Image Processing. 2017-02-01, vol. 26, n° 2, p. 549-560

Institute of Electrical and Electronics Engineers

Résumé en anglais

In this paper, we aim at super-resolving a low-resolution texture under the assumption that a high-resolution patch of the texture is available. To do so, we propose a variational method that combines two approaches, that are texture synthesis and image reconstruction. The resulting objective function holds a nonconvex energy that involves a quadratic distance to the low-resolution image, a histogram-based distance to the high-resolution patch, and a nonlocal regularization that links the missing pixels with the patch pixels. As for the histogram-based measure, we use a sum of Wasserstein distances between the histograms of some linear transformations of the textures. The resulting optimization problem is efficiently solved with a primal-dual proximal method. Experiments show that our method leads to a significant improvement, both visually and numerically, with respect to state-of-the-art algorithms for solving similar problems.< Réduire

Mots clés en anglais

Super-Resolution

Texture Synthesis

Texture Reconstruction

Wasserstein distance

Histograms

Proximal algorithms

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Texture Reconstruction guided by a High-Resolution Patch

Langue

Ce document a été publié dans

Résumé en anglais

Mots clés en anglais

URI

DOI

Origine

Unités de recherche