Structure-Aware Graph Construction For Point Cloud Segmentation With Graph Convolutional Networks

The k-nearest neighbors (KNN) algorithm has been widely adopted to construct graph convolutional networks (GCNs) for point cloud segmentation. However, the $\ell_{2}$ norm cannot discriminate the multi-dimensional structures within a point cloud. In this paper, we propose a novel structure-aware graph construction for point clouds that compensates the $\ell_{2}$ norm with per-dimension differences of the signal. The proposed method dynamically calculates the similarity ratio to determine the dimension-based proximity of the pair of points. Consequently, it improves both the spatial and spectral GCNs with the capability of aggregating information from relevant neighbors for point cloud segmentation. As a model-agnostic method, it can be seamlessly embedded into arbitrary GCN architectures during the graph construction phase. Experimental results demonstrate that the proposed method can improve classification accuracy around thejoint areas of objects.