Synthetic point cloud generation for class segmentation applications

Abstract: Maintenance of industrial facilities is a growing hazard due to the cumbersome process to identify infrastructure degradation. Digital Twins have the potential to improve maintenance by monitoring the continuous digital representation of infrastructure. However, the time needed to map the existing geometry makes their use prohibitive. We previously developed class segmentation to automate digital twinning, however a vast amount of annotated point clouds is needed. Currently, synthetic data generation for automated segmentation is nonexistent. We used Helios++ to automatically segment point clouds from IFC models. Our research has the potential to pave the ground for efficient industrial class segmentation.