Intrinsic Decompositions for Image Editing - Archive ouverte HAL Access content directly
Journal Articles Computer Graphics Forum Year : 2017

Intrinsic Decompositions for Image Editing


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.
Fichier principal
Vignette du fichier
star-intrinsic_final.pdf (80.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01483773 , version 1 (06-03-2017)


  • HAL Id : hal-01483773 , version 1


Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, Kavita Bala. Intrinsic Decompositions for Image Editing. Computer Graphics Forum, 2017, Eurographics State of the Art Reports 2017, 36 (2), pp.593-609. ⟨hal-01483773⟩
480 View
145 Download


Gmail Facebook X LinkedIn More