PIERRE, Fabien; AUJOL, Jean-François; DELEDALLE, Charles-Alban; PAPADAKIS, Nicolas

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

PIERRE, Fabien
Institut de Mathématiques de Bordeaux [IMB]

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

DELEDALLE, Charles-Alban
Institut de Mathématiques de Bordeaux [IMB]

Langue

Communication dans un congrès

Ce document a été publié dans

Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'17), 2017-10-30, Venise. p. 235-248

Résumé en anglais

This paper focuses on the denoising of chrominance channels of color images. We propose a variational framework involving TV reg-ularization that modifies the chrominance channel while preserving the input luminance of the image. The main issue of such a problem is to ensure that the denoised chrominance together with the original luminance belong to the RGB space after color format conversion. Standard methods of the literature simply truncate the converted RGB values, which lead to a change of hue in the denoised image. In order to tackle this issue, a " RGB compatible " chrominance range is defined on each pixel with respect to the input luminance. An algorithm to compute the orthogonal projection onto such a set is then introduced. Next, we propose to extend the CLEAR debiasing technique to avoid the loss of colourfulness produced by TV regularization. The benefits of our approach with respect to state-of-the-art methods are illustrated on several experiments.< Réduire

Mots clés en anglais

denoising

Colorization

color editing

color assignment

URI

https://oskar-bordeaux.fr/handle/20.500.12278/193606

Project ANR

Generalized Optimal Transport Models for Image processing - ANR-16-CE33-0010

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251