Skip to Main content Skip to Navigation
New interface
Journal articles

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.
Document type :
Journal articles
Complete list of metadata
Contributor : Jorge Lopez-Moreno Connect in order to contact the contributor
Submitted on : Thursday, December 6, 2012 - 5:22:02 PM
Last modification on : Wednesday, February 2, 2022 - 3:55:40 PM
Long-term archiving on: : Thursday, March 7, 2013 - 3:56:37 AM




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



Record views


Files downloads