Void-growing: a novel Scan-to-BIM method for manhattan world buildings from point cloud

Yuandong Pan1, Alex Braun1, André Borrmann1, Ioannis Brilakis2
1 Technical University of Munich, Germany
2 University of Cambridge, UK

DOI: 10.35490/EC3.2021.162
Abstract: The automated generation of 3D models of buildings from point clouds is under heavy research. Currently, this Scan-to-BIM process requires high manual effort, and the previous research in buildings under low occlusion level. We propose a novel “void-growing” approach that extracts walls, floors, and ceilings automatically. Different from the majority of current approaches starting with detecting surfaces of elements, our approach grows the void volume space inside a room first and it performs well in occluded environments. It can reconstruct simple cuboid rooms and complex rooms like L-shape and U-shape rooms. Different ceiling heights caused by suspended ceilings can also be represented.
Keywords: Void-growing, Scan-to-BIM, Point cloud, 3D reconstruction
Pages: 312 - 321

Presentation Video: