A LOOPY BELIEF PROPAGATION APPROACH TO THE SHAPE FROM SHADING PROBLEM

Markus Louw, Fred Nicolls, Dee Bradshaw

Abstract

This paper describes a new approach to the shape from shading problem, using loopy belief propagation which is simple and intuitive. The algorithm is called Loopy Belief Propagation Shape-From-Shading (LBP-SFS). It produces reasonable results on real and synthetic data, and surface information from sources other than the image (eg range or stereo data) can be readily incorporated as prior information about the surface elevation at any point, using this framework. In addition, this algorithm proves the use of linear interpolation at the message passing level within a loopy Bayesian network, which to the authors’ knowledge has not been previously explored.

Download


Paper Citation


in Harvard Style

Louw M., Nicolls F. and Bradshaw D. (2007). A LOOPY BELIEF PROPAGATION APPROACH TO THE SHAPE FROM SHADING PROBLEM . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 978-972-8865-73-3, pages 376-381. DOI: 10.5220/0002043903760381


in Bibtex Style

@conference{visapp07,
author={Markus Louw and Fred Nicolls and Dee Bradshaw},
title={A LOOPY BELIEF PROPAGATION APPROACH TO THE SHAPE FROM SHADING PROBLEM},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2007},
pages={376-381},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002043903760381},
isbn={978-972-8865-73-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - A LOOPY BELIEF PROPAGATION APPROACH TO THE SHAPE FROM SHADING PROBLEM
SN - 978-972-8865-73-3
AU - Louw M.
AU - Nicolls F.
AU - Bradshaw D.
PY - 2007
SP - 376
EP - 381
DO - 10.5220/0002043903760381