A Deep Point Cloud Geometry Coding Toolbox

Abstract

This short paper describes a TensorFlow toolbox for point cloud geometry coding based on deep neural networks. This coding method employs a deep auto-encoder trained with a focal loss to learn good representations for voxel occupancy. The software provides several coding parameters to achieve different rate-distortion trade-offs, and comes with pre-trained models to reproduce the results of the published paper. It also offers a number of utility functions for evaluating and comparing the codec. To our knowledge, this is the first publicly available open-source toolbox for deeplearning-based point cloud coding.