Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation

Digital reconstruction through Building Information Models (BIM) is a valuable methodology for documenting and analyzing existing buildings. Its pipeline starts with geometric acquisition. (e.g., via photogrammetry or laser scanning) for accurate point cloud collection. However, the acquired data are noisy and unstructured, and the creation of a semantically-meaningful BIM representation requires a huge computational effort, as well as expensive and time-consuming human annotations. In this paper, we propose a fully automated scan-to-BIM pipeline. The approach relies on: (i) our dataset (HePIC), acquired from two large buildings and annotated at a point-wise semantic level based on existent BIM models; (ii) a novel ad hoc deep network (BIM-Net++) for semantic segmentation, whose output is then processed to extract instance information necessary to recreate BIM objects; (iii) novel model pre-training and class re-weighting to eliminate the need for a large amount of labeled data and human intervention.

1. INTRODUCTION

Digital reconstruction of existing buildings through Building Information Models (BIMs) is becoming a popular method to document and analyze heritage and existing buildings using reality acquisition techniques. The inherent nature and purposes of BIM approaches require the combination of fast and accurate modeling of the 3D scene (by means of point cloud modeling with photogrammetry and/or laser scanning), together with some data organization algorithms. Indeed, the acquired 3D points lack an explicit structure, and labeling process is hardly automated and time-consuming.