This paper introduces DCG-Net (Dynamic Capsule Graph Network) to analyze point clouds for the tasks of classification and segmentation. DCG-Net aggregates point cloud features to build and update the graphs based on the dynamic routing mechanism of capsule networks at each layer of a convolutional network. The first layer of DGC-Net exploits the geometrical attributes of the point cloud to build a graph by neighborhood aggregation while the deeper layers of the network dynamically update the graph based on the feature space of convolutions. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet-Part. Our experimental results demonstrate that DCG-Net achieves state-of-theart performance on public datasets, 93.4% accuracy on ModelNet40, and 85.4% instance mIoU (mean Intersection over Union) on ShapeNet-Part.

No abstract