Quadratic Objective Functions for Dichromatic Model Parameters Estimation

Abstract : In this paper, we present a novel method to estimate dichromatic model parameters from a single color image. Estimation of reflectance, shading and specularity has many applications such as shape recovery, specularity removal and facilitates classical image processing and computer vision tasks such as segmentation or classification. Our method is based on two successive and independent constrained quadratic programming steps to recover the parameters of the model. Compared to recent methods, our approach has the advantage to transform a complex inverse problem into two parralelizable optimization steps that are much easier to solve. We have compared our method with recent works in the field to assess its robustness and accuracy on accessible datasets. The advantages of our method are shown by analysing qualitatively and quantitatively the resulting image decompositions.
Type de document :
Communication dans un congrès
International Conference on Digital Image Computing: Techniques and Applications, 2017, Sydney, Australia
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01606701
Contributeur : Yannick Benezeth <>
Soumis le : lundi 2 octobre 2017 - 23:01:17
Dernière modification le : vendredi 8 décembre 2017 - 10:56:43

Fichier

DICTA_2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01606701, version 1

Collections

Citation

Alexandre Krebs, Yannick Benezeth, Franck Marzani. Quadratic Objective Functions for Dichromatic Model Parameters Estimation. International Conference on Digital Image Computing: Techniques and Applications, 2017, Sydney, Australia. 〈hal-01606701〉

Partager

Métriques

Consultations de la notice

63

Téléchargements de fichiers

9