Intrinsic image decomposition as two independent deconvolution problems - Université de Bourgogne Accéder directement au contenu
Article Dans Une Revue Signal Processing: Image Communication Année : 2020

Intrinsic image decomposition as two independent deconvolution problems

Résumé

In this paper, a novel method to decompose an image into “intrinsic images” is introduced. This decomposition is based on the dichromatic model which separates the influence of specular and diffuse reflections. The separation of these components is very important in several applications of image analysis including segmentation, classification, recoloring, and specularity removal. The proposed method is based on two simple deconvolution steps. The method aims to be generic: it is applicable to any kind of image (i.e. RGB as well as multispectral) and does not rely on a learning step. The method is applied to three datasets including multispectral and RGB images. The algorithm is compared to recent algorithms from the literature and gives similar or better results than the state of the art.

Dates et versions

hal-02739814 , version 1 (02-06-2020)

Identifiants

Citer

Alexandre Krebs, Yannick Benezeth, Franck Marzani. Intrinsic image decomposition as two independent deconvolution problems. Signal Processing: Image Communication, inPress, 86, pp.115872. ⟨10.1016/j.image.2020.115872⟩. ⟨hal-02739814⟩
84 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More