A Graph-CNN for 3D Point Cloud Classification
It addresses classification of 3D point cloud data, which is important for applications like computer vision and robotics, but the approach is incremental as it builds on existing Graph-CNN methods.
The paper tackles 3D point cloud classification by developing a Graph-CNN called PointGCN, which combines localized graph convolutions with pooling operations to explore local structure, achieving competitive performance on the ModelNet benchmark with improved stability.
Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to handle data that is supported on a graph. Major challenges when working with data on graphs are that the support set (the vertices of the graph) do not typically have a natural ordering, and in general, the topology of the graph is not regular (i.e., vertices do not all have the same number of neighbors). Thus, Graph-CNNs have huge potential to deal with 3D point cloud data which has been obtained from sampling a manifold. In this paper, we develop a Graph-CNN for classifying 3D point cloud data, called PointGCN. The architecture combines localized graph convolutions with two types of graph downsampling operations (also known as pooling). By the effective exploration of the point cloud local structure using the Graph-CNN, the proposed architecture achieves competitive performance on the 3D object classification benchmark ModelNet, and our architecture is more stable than competing schemes.