Learning synthetic models for roof style classification using point clouds

摘要

Systems, apparatuses, and methods are provided for three-dimensional modeling of building roofs using three-dimensional point cloud data. Point cloud data of a roof of a building is received, and roof data points are selected or extracted from the point cloud data. Semantic type classifications are calculated for each selected roof data point. Roof styles are determined from the semantic type classifications, and a synthetic model of the roof and building is rendered based on the determined roof style.