Abstract: Automated three-dimensional (3D) building model estimation is disclosed. In an embodiment, a method comprises: obtaining, using one or more processors, an aerial image of a building based on an input address; obtaining, using the one or more processors, three-dimensional (3D) data containing the building based on the input address; pre-processing the aerial image and 3D data; reconstructing, using the one or more processors, a 3D building model from the pre-processed image and 3D data, the reconstructing including: predicting, using instance segmentation, a mask for each roof face; converting each roof face into a two-dimensional (2D) polygon; and projecting each 2D polygon into a 3D polygon representing the 3D building model.

Abstract: Described herein is a process and system for constructing three-dimensional (3D) representations of roof structures. The system can create representations of roof structures of arbitrary complexity and can create representations of dependent roof structures such as dormers. The system can create representations of roof structures that conventional methods cannot create, such as roofs with edges that are not coplanar, roofs with faces that do not connect to exterior edges, roofs composed of sub-structures, or roofs with dependent structures such as dormers.

Abstract: Described herein is a process and system for constructing three-dimensional (3D) representations of roof structures. The system can create representations of roof structures of arbitrary complexity and can create representations of dependent roof structures such as dormers. The system can create representations of roof structures that conventional methods cannot create, such as roofs with edges that are not coplanar, roofs with faces that do not connect to exterior edges, roofs composed of sub-structures, or roofs with dependent structures such as dormers.

Abstract: Described herein is a process and system for constructing three-dimensional (3D) representations of roof structures. The system can create representations of roof structures of arbitrary complexity and can create representations of dependent roof structures such as dormers. The system can create representations of roof structures that conventional methods cannot create, such as roofs with edges that are not coplanar, roofs with faces that do not connect to exterior edges, roofs composed of sub-structures, or roofs with dependent structures such as dormers.

Abstract: Described herein is a process and system for constructing three-dimensional (3D) representations of buildings. The 3D representations of buildings are semantic models that include roof nodes, roof edges, as well as roof faces with associated properties (e.g., pitch, azimuth). The system receives a 2D representation such as a roof outline including nodes connected by edges and associated data such as a height value, a pitch value, an independent structure, or a dependent structure. The system determines height values where a building structure changes. The system propagates a wavefront representing a cross-section of the building to the height values to generate 3D model edges. The 3D representation is generated based on the 3D model edges. The system can create 3D representations of buildings including roof structures of arbitrary complexity and can create representations of dependent roof structures such as dormers.

Abstract: The present invention overcomes the limitations of the prior art by exploiting properties of the projection of a three-dimensional building structure (such as a roof) onto the ground. This projection is a two-dimensional spatial graph, which can be constructed for example by a user or by an image recognition algorithm. The spatial graph is processed to recreate a three-dimensional model of the building structure.

Abstract: Systems and methods construct three-dimensional models of building structures with roofs by exploiting properties of the projection of a three-dimensional building structure onto the ground. This projection is a two-dimensional spatial graph, which can be constructed for example by a user or by an image recognition algorithm. The spatial graph is processed to recreate a three-dimensional model of the building structure.