Intrinsic Decompositions for Image Editing

Abstract : Intrinsic images are a mid-level representation of an image that decompose the image into reflectance and illumination layers. The reflectance layer captures the color/texture of surfaces in the scene, while the illumination layer captures shading effects caused by interactions between scene illumination and surface geometry. Intrinsic images have a long history in computer vision and recently in computer graphics, and have been shown to be a useful representation for tasks ranging from scene understanding and reconstruction to image editing. In this report, we review and evaluate past work on this problem. Specifically, we discuss each work in terms of the priors they impose on the intrinsic image problem. We introduce a new synthetic ground-truth dataset that we use to evaluate the validity of these priors and the performance of the methods. Finally, we evaluate the performance of the different methods in the context of image-editing applications.
Type de document :
Article dans une revue
Computer Graphics Forum, Wiley, 2017, Eurographics State of the Art Reports 2017, 36 (2)
Liste complète des métadonnées
Contributeur : Nicolas Bonneel <>
Soumis le : lundi 6 mars 2017 - 14:24:55
Dernière modification le : samedi 3 juin 2017 - 01:07:35
Document(s) archivé(s) le : mercredi 7 juin 2017 - 14:04:06


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01483773, version 1



Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, Kavita Bala. Intrinsic Decompositions for Image Editing. Computer Graphics Forum, Wiley, 2017, Eurographics State of the Art Reports 2017, 36 (2). <hal-01483773>



Consultations de
la notice


Téléchargements du document