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]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [22 references]  Display  Hide  Download
Contributor : Mateusz Kozinski <>
Submitted on : Friday, June 26, 2015 - 8:01:54 AM
Last modification on : Tuesday, February 26, 2019 - 10:14:09 AM



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. pp.79-94, ⟨10.1007/978-3-319-16817-3_6⟩. ⟨hal-01095342⟩



Record views


Files downloads