Exploiting the room structure of buildings for scalable architectural modeling of interiors

We propose a scalable strategy for the architectural modeling of large-scale interiors from 3D point clouds. We exploit the fact that buildings are structured into different rooms to cast the modeling of a large, multi-room environment as a set of simpler and independent reconstruction problems. This drastically reduces the complexity of the computation and makes the processing of large-scale datasets feasible even without using restrictive priors that affect the precision of the final output.