Semantic segmentation on Swiss3DCities: A benchmark study on aerial photogrammetric 3D pointcloud dataset

•Importance of the data size for pointcloud segmentation with deep learning.•Analyzing model generalization over cities for a deep point segmentation model.•Viability of the simple model ensembling approaches to improve performance. We introduce a new outdoor urban 3D pointcloud dataset, covering a total area of 2.7km2, sampled from three Swiss cities with different characteristics. The dataset is manually annotated for semantic segmentation with per-point labels, and is built using photogrammetry from images acquired by multirotors equipped with high-resolution cameras. In contrast to datasets acquired with ground LiDAR sensors, the resulting point clouds are uniformly dense and complete, and are useful to disparate applications, including autonomous driving, gaming and smart city planning. As a benchmark, we report quantitative results of PointNet++, an established point-based deep 3D semantic segmentation model; on this model, we additionally study the impact of using different cities for model generalization.