ConvPoint: continuous convolutions for point cloud processing

Point clouds are unstructured and unordered data, as opposed to images. Thus, most of machine learning approaches, developed for images, cannot be directly transferred to point clouds. In this paper, we propose a generalization of the discrete convolutional neural networks (CNNs) \corr{in order to} deal with sparse input point cloud. We replace the discrete kernels by continuous ones. The formulation is simple, does not set the input point cloud size and can easily be used for neural network design similarly to 2D CNNs. We present experimental results with various architectures, underlying the flexibility of the proposed approach. We obtain competitive results compared to the state of the art, on shape classification, part segmentation and semantic segmentation for large-scale clouds.