A Toolbox for Deep Point Cloud Geometry Compression
Maurice Quach, Giuseppe Valenzise, Fréderic Dufaux · HAL (Le Centre pour la Communication Scientifique Directe) · 2020
We provide 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.