EXEMPLAR-BASED COLORIZATION IN RGB COLOR SPACE

Abstract : This paper deals with the problem of image colorization. A model including total variation regularization is proposed. Our approach colorizes directly the three RGB channels, while most existing methods were only focusing on the two chrominance channels. By using the three channels, our approach is able to better preserve color consistency. Our model is non convex, but we propose an efficient primal-dual like algorithm to compute a local minimizer. Numerical examples illustrate the good behavior of our algorithm with respect to state-of-the-art methods.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01019627
Contributor : Fabien Pierre <>
Submitted on : Monday, July 7, 2014 - 11:50:11 AM
Last modification on : Tuesday, April 2, 2019 - 8:06:01 AM
Document(s) archivé(s) le : Tuesday, October 7, 2014 - 12:16:40 PM

File

pierre2014exemplar.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01019627, version 1

Collections

Citation

Fabien Pierre, Jean-François Aujol, Aurélie Bugeau, Nicolas Papadakis, Vinh-Thong Ta. EXEMPLAR-BASED COLORIZATION IN RGB COLOR SPACE. Internationnal Conference on Image Processing, Oct 2014, Paris, France. pp.1-5. ⟨hal-01019627⟩

Share

Metrics

Record views

343

Files downloads

766