Intrinsic Scene Decomposition from RGB-D Images

Mohammed Hachama, Bernard Ghanem, Peter Wonka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Scopus citations

Abstract

In this paper, we address the problem of computing an intrinsic decomposition of the colors of a surface into an albedo and a shading term. The surface is reconstructed from a single or multiple RGB-D images of a static scene obtained from different views. We thereby extend and improve existing works in the area of intrinsic image decomposition. In a variational framework, we formulate the problem as a minimization of an energy composed of two terms: a data term and a regularity term. The first term is related to the image formation process and expresses the relation between the albedo, the surface normals, and the incident illumination. We use an affine shading model, a combination of a Lambertian model, and an ambient lighting term. This model is relevant for Lambertian surfaces. When available, multiple views can be used to handle view-dependent non-Lambertian reflections. The second term contains an efficient combination of l2 and l1-regularizers on the illumination vector field and albedo respectively. Unlike most previous approaches, especially Retinex-like techniques, these terms do not depend on the image gradient or texture, thus reducing the mixing shading/reflectance artifacts and leading to better results. The obtained non-linear optimization problem is efficiently solved using a cyclic block coordinate descent algorithm. Our method outperforms a range of state-of-the-art algorithms on a popular benchmark dataset.
Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Computer Vision (ICCV)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages810-818
Number of pages9
ISBN (Print)9781467383912
DOIs
StatePublished - Feb 19 2016

Fingerprint

Dive into the research topics of 'Intrinsic Scene Decomposition from RGB-D Images'. Together they form a unique fingerprint.

Cite this