1. Introduction
Point cloud semantic segmentation aims to assign a category label for each 3D point, which can be applied to various scenarios, such as robotics [34], autonomous driving [1], and augmented reality [20]. Recently, deep learning based methods [38], [52] have achieved impressive performance. These high-performing methods usually rely on large amounts of data with point-wise labels. However, acquiring such dense labels for 3D point clouds is extremely tedious and costly.