Beyond Procedural Facade Parsing: Bidirectional Alignment via Linear Programming

Mateusz Koziński 1, 2 Guillaume Obozinski 1, 2 Renaud Marlet 1, 2
1 IMAGINE [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : We propose a novel formulation for parsing facade images with user-defined shape prior. Contrary to other state-of-the-art methods, we do not explore the procedural space of shapes derived from a grammar. Instead we formulate parsing as a linear binary program which we solve using dual decomposition. The algorithm produces plausible approximations of globally optimal segmentations without grammar sampling. It yields state-of-the-art performance on standard datasets.
Type de document :
Communication dans un congrès
2014 Asian Conference on Computer Vision (ACCV), Nov 2014, Singapore, Singapore. Springer, 9006, pp.79-94, Computer Vision -- ACCV 2014 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers. 〈10.1007/978-3-319-16817-3_6〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01095342
Contributeur : Mateusz Kozinski <>
Soumis le : vendredi 26 juin 2015 - 08:01:54
Dernière modification le : mercredi 4 juillet 2018 - 16:33:29

Identifiants

Citation

Mateusz Koziński, Guillaume Obozinski, Renaud Marlet. Beyond Procedural Facade Parsing: Bidirectional Alignment via Linear Programming. 2014 Asian Conference on Computer Vision (ACCV), Nov 2014, Singapore, Singapore. Springer, 9006, pp.79-94, Computer Vision -- ACCV 2014 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers. 〈10.1007/978-3-319-16817-3_6〉. 〈hal-01095342〉

Partager

Métriques

Consultations de la notice

372

Téléchargements de fichiers

67