Hausdorff Point Convolution with Geometric Priors
This work provides an incremental improvement in 3D point cloud semantic segmentation for researchers and practitioners working with geometric deep learning.
This paper introduces Hausdorff Point Convolution (HPC), a shape-aware method for 3D point cloud feature learning using Hausdorff distance and a compact set of four geometric prior kernels. The resulting HPC-DNN achieved a 2.8% mIoU performance boost on S3DIS and 1.5% on SemanticKITTI for semantic segmentation compared to strong baselines like KPConv.
Without a shape-aware response, it is hard to characterize the 3D geometry of a point cloud efficiently with a compact set of kernels. In this paper, we advocate the use of Hausdorff distance as a shape-aware distance measure for calculating point convolutional responses. The technique we present, coined Hausdorff Point Convolution (HPC), is shape-aware. We show that HPC constitutes a powerful point feature learning with a rather compact set of only four types of geometric priors as kernels. We further develop a HPC-based deep neural network (HPC-DNN). Task-specific learning can be achieved by tuning the network weights for combining the shortest distances between input and kernel point sets. We also realize hierarchical feature learning by designing a multi-kernel HPC for multi-scale feature encoding. Extensive experiments demonstrate that HPC-DNN outperforms strong point convolution baselines (e.g., KPConv), achieving 2.8% mIoU performance boost on S3DIS and 1.5% on SemanticKITTI for semantic segmentation task.