cvpr cvpr2013 cvpr2013-57 cvpr2013-57-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Andelo Martinovic, Luc Van_Gool
Abstract: Within the fields of urban reconstruction and city modeling, shape grammars have emerged as a powerful tool for both synthesizing novel designs and reconstructing buildings. Traditionally, a human expert was required to write grammars for specific building styles, which limited the scope of method applicability. We present an approach to automatically learn two-dimensional attributed stochastic context-free grammars (2D-ASCFGs) from a set of labeled buildingfacades. To this end, we use Bayesian Model Merging, a technique originally developed in the field of natural language processing, which we extend to the domain of two-dimensional languages. Given a set of labeled positive examples, we induce a grammar which can be sampled to create novel instances of the same building style. In addition, we demonstrate that our learned grammar can be used for parsing existing facade imagery. Experiments conducted on the dataset of Haussmannian buildings in Paris show that our parsing with learned grammars not only outperforms bottom-up classifiers but is also on par with approaches that use a manually designed style grammar.
[1] D. G. Aliaga, P. A. Rosen, and D. R. Bekins. Style grammars for interactive visualization of architecture. TVCG, 13(4), 2007. 2
[2] M. Bokeloh, M. Wand, and H.-P. Seidel. A connection between partial symmetry and inverse procedural modeling. SIGGRAPH, 29(4), 2010. 2
[3] E. M. Gold. Language identification in the limit. Information and Control, 10(5), 1967. 2
[4] P. J. Green. Reversible jump markov chain monte carlo computation and bayesian model determination. Biometrika, 82(4), 1995. 6
[5] F. Han and S.-C. Zhu. Bottom-up/top-down image
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14] parsing with attribute grammar. IEEE TPAMI, 3 1(1), 2009. 2 J. J. Horning. A study of grammatical inference. PhD thesis, Stanford, CA, USA, 1969. AAI7010465. 2 I. Hwang, A. Stuhlmüller, and N. D. Goodman. Inducing probabilistic programs by bayesian program merging. CoRR, arXiv: 1110.5667, 2011. 2 A. Martinovi c´, M. Mathias, J. Weissenberg, and L. Van Gool. A three-layered approach to facade parsing. In ECCV, 2012. 7 A. Martinovi c´ and L. Van Gool. Earley parsing for 2D stochastic context free grammars. Technical Report KUL/ESAT/PSI/1301, KU Leuven, 2013. 4 M. Mathias, A. Martinovi c´, J. Weissenberg, and L. Van Gool. Procedural 3D building reconstruction using shape grammars and detectors. In 3DIMPVT, 2011. 1 P. Müller, P. Wonka, S. Haegler, A. Ulmer, and L. Van Gool. Procedural modeling of buildings. SIGGRAPH, 25(3), 2006. 1 P. Muller, G. Zeng, P. Wonka, and L. Van Gool. Image-based procedural modeling of facades. SIGGRAPH, 26(3), 2007. 2 Olivier Teboul. Ecole Centrale Paris Facades Database. http : / /www .ma s . e cp . fr /vi s i / on P e rs onne l eboul / dat a .php, 2010. 7 /t Procedural. CityEngine. http : / /www . procedural . com/ , 2010. 7
[15] H. Riemenschneider, U. Krispel, W. Thaller, M. Donoser, S. Havemann, D. W. Fellner, and H. Bischof. Irregular lattices for complex shape grammar facade parsing. In CVPR, 2012. 2, 3, 5
[16] N. Ripperda and C. Brenner. Reconstruction of façade structures using a formal grammar and rjmcmc. In DAGM, 2006. 1, 2
[17] G. Stiny. Pictorial and formal aspects of shape and shape grammars, 1975. Birkhauser Verlag, Basel. 1
[18] A. Stolcke. Bayesian Learning of Probabilistic Language Models. PhD thesis, University of California at Berkeley, 1994. 2, 4
[19] J. O. Talton, Y. Lou, S. Lesser, J. Duke, R. M eˇch, and V. Koltun. Metropolis procedural modeling. SIGGRAPH, 30(2), 2011. 2, 5, 6
[20] J. O. Talton, L. Yang, R. Kumar, M. Lim, N. D. Goodman, and R. M eˇch. Learning design patterns with bayesian grammar induction. In UIST, 2012. 2
[21] O. Teboul, I. Kokkinos, L. Simon, P. Koutsourakis, and N. Paragios. Shape grammar parsing via reinforcement learning. In CVPR, 2011. 1, 5, 6, 7
[22] O. Teboul, L. Simon, P. Koutsourakis, and N. Paragios. Segmentation of building facades using procedural shape priors. In CVPR, 2010. 2, 6, 7
[23] A. Toshev, P. Mordohai, and B. Taskar. Detecting and parsing architecture at city scale from range data. In CVPR, 2010. 1
[24] C. Vanegas, D. Aliaga, and B. Beneš. Building recon-
[25]
[26]
[27]
[28] struction using manhattan-world grammars. In CVPR, 2010. 1 C. A. Vanegas, D. G. Aliaga, P. Wonka, P. Müller, P. Waddell, and B. Watson. Modelling the appearance and behaviour of urban spaces. Comput. Graph. Forum, 29(1), 2010. 1 O. Št’ava, B. Beneš, R. M eˇch, D. G. Aliaga, and P. Krištof. Inverse procedural modeling by automatic generation of l-systems. Computer Graphics Forum, 29(2), 2010. 2 P. Wonka, M. Wimmer, F. X. Sillion, and W. Ribarsky. Instant architecture. SIGGRAPH, 22(3), 2003. 1 D. H. Younger. Recognition and parsing of contextfree languages in time n3. Information and Control, 10(2), 1967. 4 222000888