Digitization of Existing Buildings with Arbitrary Shaped Spaces from Point Clouds

Abstract

Digital Twins for buildings can significantly reduce building operation costs. However, existing methods for constructing geometric digital twins fail to model the complex geometry of indoor environments. To address this problem, this paper proposes a novel method for digitising building geometry with arbitrary shapes of spaces by detecting empty regions in point clouds and then expanding them to occupy the entire indoor space. The detected spaces are then used to detect structural objects and transition between spaces, such as doors, without assuming their geometric properties. The method reconstructs the volumetric representation of individual spaces, detects walls, windows and doors between them and splits the PCD into point clusters of individual spaces from large-scale cluttered PCDs of complex environments. We conduct extensive experiments on S3DIS and TUMCMS datasets and show that the proposed method outperforms existing methods for digitising Manhatten-world buildings. In contrast to existing approaches, the method allows digitising buildings with arbitrarily shaped spaces, including complex layouts, non-flat, non-vertical walls, and non-flat, non-horizontal floors and ceilings.