Building segmentation from airborne vhr images using mask r-cnn

Up-to-date 3D building models are important for many applications. Airborne very high resolution (VHR) images often acquired annually give an opportunity to create an up-to-date 3D model. Building segmentation is often the first and utmost step. Convolutional neural networks (CNNs) draw lots of attention in interpreting VHR images as they can...

HSW: Heuristic Shrink-wrapping for automatically repairing solid-based CityGML LOD2 building models

The Level-of-Detail (LOD) 2 building models defined in CityGML are used widely in three-dimensional (3D) city applications. Many of these applications demand valid solid-based geometry (closed 2-manifold), which is crucial for analytical and computational purposes. However, this condition is often violated in practice because of the way LOD2...

Automatic generation of medium-detailed 3D models of buildings based on CAD data

We present the preliminary results of a work in progress which aims to obtain a software system able to automatically generate a set of diverse 3D building models with a medium level of detail, that is, more detailed that a mere parallelepiped, but not as detailed as a complete geometric representation of the building. Each building model is...