PointNGCNN: Deep convolutional networks on 3D point clouds with neighborhood graph filters

Despite great success of deep neural networks for 2D vision tasks, point clouds, unlike 2D images, cannot be directly applied to traditional convolutional neural networks because of irregularities in the form of data. In this paper, we develop a novel end-to-end deep learning network called PointNGCNN that can consume point clouds for 3D object recognition and segmentation tasks. In order to extract the neighborhood geometric features, we propose to construct a neighborhood graph that reflects the relationship between the neighborhood points of each point and then use the Chebyshev polynomials as the neighborhood graph filters. Further, we put the feature matrix and Laplacian matrix of each neighborhood into the network and use the max pooling operation to get the features of each center. Experimental results on benchmark datasets demonstrate that PointNGCNN has achieved good performance in the recognition and segmentation tasks. (C) 2019 Elsevier Ltd. All rights reserved.