Reconstructing facade details using MLS point clouds and Bag-of-Words approach
This addresses the challenge of realistic facade reconstruction for applications like automated driving testing or solar potential estimation, though it appears incremental.
The paper tackles the problem of reconstructing 3D facade details by combining MLS point clouds with a 3D model library using an augmented Bag-of-Words approach with semi-global features, showing promising results that improve upon conventional methods.
In the reconstruction of façade elements, the identification of specific object types remains challenging and is often circumvented by rectangularity assumptions or the use of bounding boxes. We propose a new approach for the reconstruction of 3D façade details. We combine MLS point clouds and a pre-defined 3D model library using a BoW concept, which we augment by incorporating semi-global features. We conduct experiments on the models superimposed with random noise and on the TUM-FAÇADE dataset. Our method demonstrates promising results, improving the conventional BoW approach. It holds the potential to be utilized for more realistic facade reconstruction without rectangularity assumptions, which can be used in applications such as testing automated driving functions or estimating façade solar potential.