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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Teboul, O., Simon, L., Koutsourakis, P., Paragios, N.: Segmentation of building facades using procedural shape priors. In: CVPR, pp. 3105–3112 (2010)
Teboul, O., Kokkinos, I., Simon, L., Koutsourakis, P., Paragios, N.: Shape grammar parsing via reinforcement learning. In: CVPR, pp. 2273–2280 (2011)
Riemenschneider, H., Krispel, U., Thaller, W., Donoser, M., Havemann, S., Fellner, D., Bischof, H.: Irregular lattices for complex shape grammar facade parsing. In: CVPR (2012)
Zhu, S.C., Mumford, D.: A stochastic grammar of images. Found. Trends Comput. Graph. Vis. 2, 259–362 (2006)
Stiny, G.N.: Pictorial and Formal Aspects of Shape and Shape Grammars and Aesthetic Systems. PhD thesis, University of California, Los Angeles (1975). AAI7526993
Ohta, Y., Kanade, T., Sakai, T.: An analysis system for scenes containing objects with substructures. In: Proceedings of the Fourth International Joint Conference on Pattern Recognitions, pp. 752–754 (1978)
Ohta, Y., Kanade, T., Sakai, T.: A production system for region analysis. In: Proceedings of the Sixth International Joint Conference on Artificial Intelligence, pp. 684–686 (1979)
Han, F., Zhu, S.C.: Bottom-up/top-down image parsing with attribute graph grammar. IEEE Trans. Pattern Anal. Mach. Intell. 31, 59–73 (2009)
Wang, W., Pollak, I., Wong, T.S., Bouman, C.A., Harper, M.P.: Hierarchical stochastic image grammars for classification and segmentation. IEEE Trans. Image Process. 15, 3033–3052 (2006)
Jin, Y., Geman, S.: Context and hierarchy in a probabilistic image model. In: CVPR (2), pp. 2145–2152 (2006)
Ahuja, N., Todorovic, S.: Connected segmentation tree - a joint representation of region layout and hierarchy. In: CVPR (2008)
Müller, P., Wonka, P., Haegler, S., Ulmer, A., Van Gool, L.: Procedural modeling of buildings. ACM Trans. Graph. 25, 614–623 (2006)
Teboul, O.: Shape Grammar Parsing: Application to Image-based Modeling. PhD thesis, Ecole centrale Paris (2011)
Koziński, M., Marlet, R.: Image parsing with graph grammars and Markov random fields. In: WACV (2014)
Martinovic, A., Mathias, M., Weissenberg, J., Van Gool, L.: A three-layered approach to facade parsing. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012 Part VII. LNCS, vol. 7578, pp. 416–429. Springer, Heidelberg (2012)
Cohen, A., Schwing, A., Pollefeys, M.: Efficient structured parsing of facades using dynamic programming. In: CVPR (2014)
Komodakis, N., Paragios, N., Tziritas, G.: MRF energy minimization and beyond via dual decomposition. IEEE Trans. PAMI 33, 531–552 (2011)
Sontag, D., Globerson, A., Jaakkola, T.: Introduction to dual decomposition for inference. In: Sra, S., Nowozin, S., Wright, S.J. (eds.) Optimization for Machine Learning. MIT Press, Cambridge (2011)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3, 1–122 (2011)
Ladický, L., Russell, C., Kohli, P., Torr, P.H.S.: Associative hierarchical random fields. IEEE Trans. Pattern Anal. Mach. Intell. 99, 1 (2013)
Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)
Komodakis, N.: Efficient training for pairwise or higher order CRFs via dual decomposition. In: CVPR, pp. 1841–1848 (2011)
Acknowledgements
This work was carried out in IMAGINE, a joint research project between Ecole des Ponts ParisTech (ENPC) and the Scientific and Technical Centre for Building (CSTB). It was partly supported by ANR project Semapolis ANR-13-CORD-0003.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Koziński, M., Obozinski, G., Marlet, R. (2015). Beyond Procedural Facade Parsing: Bidirectional Alignment via Linear Programming. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)