Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
This addresses the problem of accurate 3D scene understanding for applications like robotics and autonomous driving, representing an incremental improvement over existing methods.
The paper tackles 3D semantic segmentation of unstructured point clouds by introducing grouping techniques for neighborhoods in world and feature spaces, along with dedicated loss functions, achieving state-of-the-art performance on indoor and outdoor datasets.
In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce grouping techniques which define point neighborhoods in the initial world space and the learned feature space. Neighborhoods are important as they allow to compute local or global point features depending on the spatial extend of the neighborhood. Additionally, we incorporate dedicated loss functions to further structure the learned point feature space: the pairwise distance loss and the centroid loss. We show how to apply these mechanisms to the task of 3D semantic segmentation of point clouds and report state-of-the-art performance on indoor and outdoor datasets.