Proceedings of the 2022 European Conference on Computing in Construction


SemDpray: Virtual reality as-is semantic information labeling tool for 3D spatial data

Yiming Zhao, Cyprien Fol, Yuchang Jiang, Tianyu Wu, Iro Armeni
ETH Zurich, Switzerland

DOI: 10.35490/EC3.2022.175
Abstract: Capturing the as-is status of buildings in the form of 3D spatial data has been becoming more accurate and efficient, but the act of extracting from it as-is information has not seen similar advancements. State-of-the-art practice requires experts to manually interact with the spatial data in a laborious and time-consuming process. We propose Semantic Spray (Semspray), a Virtual Reality (VR) application that provides users with intuitive tools to produce semantic information on as-is 3D spatial data of buildings. The goal is to perform this task accurately and more efficiently by allowing users to interact with the data at different scales.
Keywords: virtual reality, semantic segmentation, as-is building information

Presentation Video: