Layout graph model for semantic façade reconstruction using laser point clouds

Building façades can feature different patterns depending on the architectural style, functionality, and size of buildings; therefore, reconstructing these be complicated. In particular, when semantic are reconstructed from point cloud data, uneven density noise make it difficult to accurately determine façade structure. When investigating layouts, Gestalt principles applied cluster visually similar floors elements, allowing for a more intuitive interpretation structures. We propose novel model describing structures, namely layout graph model, which involves compound with two structure levels. proposed elements such as windows first grouped into clusters. A down-layout is then formed using this node by combining intra- inter-cluster spacings edges. Second, top-layout clustering floors. By extracting relevant parameters we transform reconstruction an optimization strategy simulated annealing coupled Gibbs sampling. Multiple data features were selected three datasets verify effectiveness method. The experimental results show that method achieves average accuracy 86.35%. Owing its flexibility, deal types qualities enabling robust accurate models.