Evangelou, IordanisVitsas, NickPapaioannou, GeorgiosGeorgioudakis, ManolisChatzisymeon, ApostolosBiasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.2021-09-012021-09-012021978-3-03868-137-31997-0471https://doi.org/10.2312/3dor.20211306https://diglib.eg.org:443/handle/10.2312/3dor20211306The Building Information Modelling (BIM) procedure introduces specifications and data exchange formats widely used by the construction industry to describe functional and geometric elements of building structures in the design, planning, cost estimation and construction phases of large civil engineering projects. In this paper we explain how to apply a modern, low-parameter, neural-network-based classification solution to the automatic geometric BIM element labeling, which is becoming an increasingly important task in software solutions for the construction industry. The network is designed so that it extracts features regarding general shape, scale and aspect ratio of each BIM element and be extremely fast during training and prediction. We evaluate our network architecture on a real BIM dataset and showcase accuracy that is difficult to achieve with a generic 3D shape classification network.Computing methodologiesNeural networksShape analysis10.2312/3dor.202113061-4