Intrinsic Scene Decomposition from RGB-D Images

Handle URI:
http://hdl.handle.net/10754/605194
Title:
Intrinsic Scene Decomposition from RGB-D Images
Authors:
Hachama, Mohammed; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Wonka, Peter ( 0000-0003-0627-9746 )
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.
KAUST Department:
Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Visual Computing Center (VCC)
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2015 IEEE International Conference on Computer Vision (ICCV)
Conference/Event name:
2015 IEEE International Conference on Computer Vision (ICCV)
Issue Date:
7-Dec-2015
DOI:
10.1109/ICCV.2015.99
Type:
Conference Paper
Sponsors:
Research reported in this publication was supported by competitive research funding from King Abdullah University of Science and Technology (KAUST) with grant number OCRF-2014-CRG3-62140401 and by a post-doctoral fellowship from the Saudi Arabia Basic Industries Corporation (SABIC).
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7410456
Appears in Collections:
Conference Papers; Computer Science Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHachama, Mohammeden
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorWonka, Peteren
dc.date.accessioned2016-04-13T13:28:14Zen
dc.date.available2016-04-13T13:28:14Zen
dc.date.issued2015-12-07en
dc.identifier.doi10.1109/ICCV.2015.99en
dc.identifier.urihttp://hdl.handle.net/10754/605194en
dc.description.abstractIn 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.en
dc.description.sponsorshipResearch reported in this publication was supported by competitive research funding from King Abdullah University of Science and Technology (KAUST) with grant number OCRF-2014-CRG3-62140401 and by a post-doctoral fellowship from the Saudi Arabia Basic Industries Corporation (SABIC).en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7410456en
dc.rights(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.titleIntrinsic Scene Decomposition from RGB-D Imagesen
dc.typeConference Paperen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2015 IEEE International Conference on Computer Vision (ICCV)en
dc.conference.date7-13 Dec. 2015en
dc.conference.name2015 IEEE International Conference on Computer Vision (ICCV)en
dc.conference.locationSantiagoen
dc.eprint.versionPost-printen
kaust.authorHachama, Mohammeden
kaust.authorGhanem, Bernarden
kaust.authorWonka, Peteren
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.