Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing
challenge. Unlike mesh-based models, they require watertight geometry and object-wise
semantics at the facade level. The principal challenge of such demanding semantic 3D
reconstruction is reliable facade-level semantic segmentation of 3D input data. We present a
novel method, called Scan2LoD3, that accurately reconstructs semantic LoD3 building
models by improving facade-level semantic 3D segmentation. To this end, we leverage laser …