Boulch, AlexandreBiasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco2019-05-042019-05-042019978-3-03868-077-21997-0471https://doi.org/10.2312/3dor.20191064https://diglib.eg.org:443/handle/10.2312/3dor20191064Point 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. It usually requires data transformation such as voxelization, inducing a possible loss of information. In this paper, we propose a generalization of the discrete convolutional neural networks (CNNs) able 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, competitive with the state of the art, on shape classification, part segmentation and semantic segmentation for large scale clouds.Computing methodologiesMachine LearningComputer graphicsPointbased modelsShape analysis10.2312/3dor.2019106471-78