An imaging camera (212) and a depth camera (302, 304, 306) are configured to perform a 3D scan of an interior space (100, 1600). A processor (1510) is configured to generate voxels in a three-dimensional (3D) grid based on the 3D scan. The voxels represent portions of the volume of the in terior space. The processor is also configured to project the voxels onto tiles (620, 920) in a 2D floor plan (2100) of the interior space, and to generate, based on the tiles, a 2D distance grid (700) that represents features in the interior space. The processor is further configured to generate, based on a 2D distance grid, a set of polygons (801, 802, 803) representing elements of the floor plan in real-time. The processor is further configured to generate a simplified set of primitives (1205) representing the floor plan.