We address the problem of parsing images of building facades. The goal is to segment images, assigning to the resulting regions semantic labels that correspond to the basic architectural elements. We assume a top-down parsing framework based on a 2D shape grammar that encodes a prior knowledge on the possible composition of facades. The algorithm explores the space of feasible solutions by generating the possible configurations of the facade and comparing it to the input data by means of a local, pixelor patch-based classifier. We propose new bottom-up cues for the algorithm, both for evaluation of a candidate parse and for guiding the exploration of the space of feasible solutions. The method that we propose benefits from detectionbased information and leverages on the similar appearance of elements that repeat in a given facade. Experiments performed on standard datasets show that this use of more discriminative bottom-up cues improves the convergence in comparison to state-of-the-art algorithms, and gives better results in terms of precision and recall, as well as computation time and performance deviation.

Abstract. We propose a robust method to match image feature points taking into account geometric consistency. It is a careful adaptation of the match propagation principle to 4th-order geometric constraints (match quadruple consistency). With our method, a set of matches is explained by a network of locally-similar affinities. This approach is useful when simple descriptor-based matching strategies fail, in particular for highly ambiguous data, e.g., with repetitive patterns or where texture is lacking. As it scales easily to hundreds of thousands of matches, it is also useful when denser point distributions are sought, e.g., for high-precision rigid model estimation. Experiments show that our method is competitive (efficient, scalable, accurate, robust) against state-of-the-art methods in deformable object matching, camera calibration and pattern detection.