Detecting and inferring repetitive elements with accurate locations and shapes from facades

The use of repetition detection is an effective approach for increasing the efficiency of urban modeling. In practice, repetition detection can benefit from the apparent regularities and strong contextual relationships in facades. In view of this, we propose a novel algorithm for automatically detecting and inferring repetitive elements with accurate locations and shapes from facades. More specifically, firstly, starting from a rectification of the input facade, we employ the color clustering method to automatically derive candidate templates. Secondly, to detect the non- and partially occluded repetitive elements matching with the derived templates, we construct an adaptive region descriptor and a repetitive characteristic curve. Finally, the fully occluded elements are inferred by utilizing the Bayesian probability network, which can be learned from a database of the selected facades. The accuracy of our detection and inference is tested through a variety of experiments, and all of them justify the robustness of our algorithm to outliers such as appearance variations and occlusions.