Intrinsic Images by Clustering

Abstract : Decomposing an input image into its intrinsic shading and reflectance components is a long-standing ill-posed problem. We present a novel algorithm that requires no user strokes and works on a single image. Based on simple assumptions about its reflectance and luminance, we first find clusters of similar reflectance in the image, and build a linear system describing the connections and relations between them. Our assumptions are less restrictive than widely-adopted Retinex-based approaches, and can be further relaxed in conflicting situations. The resulting system is robust even in the presence of areas where our assumptions do not hold. We show a wide variety of results, including natural images, objects from the MIT dataset and texture images, along with several applications, proving the versatility of our method.
Type de document :
Article dans une revue
Computer Graphics Forum, Wiley, 2012, Rendering 2012, 31 (4), pp.1415-1425. 〈10.1111/j.1467-8659.2012.03137.x〉
Liste complète des métadonnées
Contributeur : Jorge Lopez-Moreno <>
Soumis le : jeudi 6 décembre 2012 - 17:22:02
Dernière modification le : jeudi 14 février 2019 - 15:33:33
Document(s) archivé(s) le : jeudi 7 mars 2013 - 03:56:37




Elena Garces, Adolfo Munoz, Jorge Lopez-Moreno, Diego Gutiérrez. Intrinsic Images by Clustering. Computer Graphics Forum, Wiley, 2012, Rendering 2012, 31 (4), pp.1415-1425. 〈10.1111/j.1467-8659.2012.03137.x〉. 〈hal-00761400〉



Consultations de la notice


Téléchargements de fichiers