A task‐driven sampling method based on graph convolution for 3D point cloud compression

Abstract

AbstractThe previous point cloud compression methods only consider reducing the amount of data. However, in applications such as autonomous driving, the compression methods not only require smooth transmission, but also ensure the efficiency of downstream tasks. To this end, a task‐driven sampling network based on graph convolution is proposed to achieve point cloud compression and recovery. First, a downsampling network is presented to simplify and compress the point cloud, in order to optimize the compressed point cloud for downstream tasks, the task loss is added to loss function for end‐to‐end training. Then, an upsampling network with residual correction unit is presented to recover and reconstruct the point cloud. Experiments for point cloud classification task on ModelNet40 dataset show that the compressed point cloud obtained through our network can achieve higher classification accuracy compared to other similar methods, and the reconstructed point cloud can further improve classification accuracy.