Hue Constrained Image Colorization in the RGB Space
PIERRE, Fabien
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Voir plus >
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
PIERRE, Fabien
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
< Réduire
Institut de Mathématiques de Bordeaux [IMB]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Langue
en
Document de travail - Pré-publication
Résumé en anglais
This work proposes a novel variational frame- work for exemplar-based image colorization in RGB while most of existing methods use a luminance-chro- minance space. Using directly these three RGB chan- nels, our model does ...Lire la suite >
This work proposes a novel variational frame- work for exemplar-based image colorization in RGB while most of existing methods use a luminance-chro- minance space. Using directly these three RGB chan- nels, our model does not need any pre or post-pro- cessing step. We design a primal-dual like algorithm that solves the proposed variational approach. The constraint when colorizing a gray-scale image is to maintain its luminance. In our RGB model this constraint is added in the variational model. Its preservation requires introducing a novel projection scheme that takes care of the hue value (H) of the HSI color-space. The behavior of our algorithm is illustrated on numerous examples, and a qualitative comparison is made with state-of-the-art methods.< Réduire
Mots clés en anglais
non-local method
Mots clés en italien
Colorization
Optimization
Color-space
non-local method.
Origine
Importé de halUnités de recherche