TUM-FAcCADE: Reviewing and enriching point cloud benchmarks for faccade segmentation

Point clouds are widely regarded as one of the best dataset types for urban mapping purposes. Hence, point cloud datasets are commonly investigated as benchmark types for various urban interpretation methods. Yet, few researchers have addressed the use of point cloud benchmarks for faccade segmentation. Robust faccade segmentation is becoming a key factor in various applications ranging from simulating autonomous driving functions to preserving cultural heritage. In this work, we present a method of enriching existing point cloud datasets with faccade-related classes that have been designed to facilitate faccade segmentation testing. We propose how to efficiently extend existing datasets and comprehensively assess their potential for faccade segmentation. We use the method to create the TUM-FAcCADE dataset, which extends the capabilities of TUM-MLS-2016. Not only can TUM-FAcCADE facilitate the development of point-cloud-based faccade segmentation tasks, but our procedure can also be applied to enrich further datasets.