Irregular lattices for complex shape grammar facade parsing

Abstract

High-quality urban reconstruction requires more than multi-view reconstruction and local optimization. The structure of facades depends on the general layout, which has to be optimized globally. Shape grammars are an established method to express hierarchical spatial relationships, and are therefore suited as representing constraints for semantic facade interpretation. Usually inference uses numerical approximations, or hard-coded grammar schemes. Existing methods inspired by classical grammar parsing are not applicable on real-world images due to their prohibitively high complexity. This work provides feasible generic facade reconstruction by combining low-level classifiers with mid-level object detectors to infer an irregular lattice. The irregular lattice preserves the logical structure of the facade while reducing the search space to a manageable size. We introduce a novel method for handling symmetry and repetition within the generic grammar. We show competitive results on two datasets, namely the Paris2010 and the Graz50. The former includes only Hausmannian, while the latter includes Classicism, Biedermeier, Historicism, Art Nouveau and post-modern architectural styles

A Survey of Algorithmic Shapes

“…The work of HAYKO RIEMENSCHNEIDER et al [76] utilizes shape grammars to enhance the results of a machine learning classifier that is pre-trained to classify pixels of an orthophoto of a facade into categories, like windows, walls, doors and sky. The system applies techniques from formal language parsing to parse a two-dimensional split grammar consisting of horizontal and vertical splits, as well as repetition and symmetry operations.…”

Parametric Models of Facade Designs of High-Rise Residential Buildings

“…Even an irregular lattice on facades can be inferred by combining low-level classifiers with mid-level parses by grammars. The irregular lattice keeps the logical framework of the facade while providing the possibilities of varieties of elements of facade patterns [10]. These concepts inspire us to set up a classified form framework of building facades by shape grammar.…”

Image parsing with graph grammars and Markov Random Fields applied to facade analysis

“…We call the above scheme 'late fusion', because it uses detections directly in the energy formulation, contrary to the 'early fusion' [14,16,17,23], where detections are projected down to pixel level and energy is evaluated on individual pixels only. Together with the detection-based potential presented below, late fusion prevents the effect of 'blurring' detections by early fusion, presented in Fig.…”

“…The problem of grammar-based facade analysis has recently received a considerable attention in the computer vision community [13,16,17,23]. The aim is to segment an input image in such a way that the result belongs to the language generated by a given shape grammar.…”