IMAGE COMPLETION USING A DIFFUSION DRIVEN MEAN CURVATURE FLOW IN A SUB-RIEMANNIAN SPACE

Gonzalo Sanguinetti, Giovanna Citti, Alessandro Sarti

2008

Abstract

In this paper we present an implementation of a perceptual completion model performed in the three dimensional space of position and orientation of level lines of an image. We show that the space is equipped with a natural subriemannian metric. This model allows to perform disocclusion representing both the occluding and occluded objects simultaneously in the space. The completion is accomplished by computing minimal surfaces with respect to the non Euclidean metric of the space. The minimality is achieved via diffusion driven mean curvature flow. Results are presented in a number of cognitive relevant cases.

Paper Citation

in Harvard Style

Sanguinetti G., Citti G. and Sarti A. (2008). IMAGE COMPLETION USING A DIFFUSION DRIVEN MEAN CURVATURE FLOW IN A SUB-RIEMANNIAN SPACE . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 46-53. DOI: 10.5220/0001075800460053

in Bibtex Style

@conference{visapp08,
author={Gonzalo Sanguinetti and Giovanna Citti and Alessandro Sarti},
title={IMAGE COMPLETION USING A DIFFUSION DRIVEN MEAN CURVATURE FLOW IN A SUB-RIEMANNIAN SPACE},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={46-53},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001075800460053},
isbn={978-989-8111-21-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - IMAGE COMPLETION USING A DIFFUSION DRIVEN MEAN CURVATURE FLOW IN A SUB-RIEMANNIAN SPACE
SN - 978-989-8111-21-0
AU - Sanguinetti G.
AU - Citti G.
AU - Sarti A.
PY - 2008
SP - 46
EP - 53
DO - 10.5220/0001075800460053