A MRF Shape Prior for Facade Parsing with Occlusions

Mateusz Koziński 1, 2, 3 Raghudeep Gadde 3, 4, 1, 2 Sergey Zagoruyko 1, 2, 3 Guillaume Obozinski 1, 3, 2 Renaud Marlet 2, 1, 3
3 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : We present a new shape prior formalism for the segmentation of rectified facade images. It combines the simplicity of split grammars with unprecedented expressive power: the capability of encoding simultaneous alignment in two dimensions, facade occlusions and irregular boundaries between facade elements. We formulate the task of finding the most likely image segmentation conforming to a prior of the proposed form as a MAP-MRF problem over a 4-connected pixel grid, and propose an efficient optimization algorithm for solving it. Our method simultaneously segments the visible and occluding objects, and recovers the structure of the occluded facade. We demonstrate state-of-the-art results on a number of facade segmentation datasets.
Type de document :
Communication dans un congrès
Conference on Computer Vision and Pattern Recognition (CVPR 2015), Jun 2015, Boston, Massachusetts, United States. IEEE, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), pp.2820-2828, 2015, Conference on Computer Vision and Pattern Recognition (CVPR 2015). 〈http://www.pamitc.org/cvpr15/〉. 〈10.1109/CVPR.2015.7298899〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal-enpc.archives-ouvertes.fr/hal-01232598
Contributeur : Renaud Marlet <>
Soumis le : lundi 23 novembre 2015 - 17:25:10
Dernière modification le : mercredi 30 mai 2018 - 17:22:02
Document(s) archivé(s) le : vendredi 28 avril 2017 - 16:56:26

Identifiants

Citation

Mateusz Koziński, Raghudeep Gadde, Sergey Zagoruyko, Guillaume Obozinski, Renaud Marlet. A MRF Shape Prior for Facade Parsing with Occlusions. Conference on Computer Vision and Pattern Recognition (CVPR 2015), Jun 2015, Boston, Massachusetts, United States. IEEE, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), pp.2820-2828, 2015, Conference on Computer Vision and Pattern Recognition (CVPR 2015). 〈http://www.pamitc.org/cvpr15/〉. 〈10.1109/CVPR.2015.7298899〉. 〈hal-01232598〉

Partager

Métriques

Consultations de la notice

409

Téléchargements de fichiers

199