English

Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression

Computer Vision and Pattern Recognition 2020-02-19 v2 Machine Learning Image and Video Processing Machine Learning

Abstract

Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .

Keywords

Cite

@article{arxiv.1903.08548,
  title  = {Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression},
  author = {Maurice Quach and Giuseppe Valenzise and Frederic Dufaux},
  journal= {arXiv preprint arXiv:1903.08548},
  year   = {2020}
}

Comments

Published in ICIP 2019. The source code can be found at https://github.com/mauriceqch/pcc_geo_cnn and the supplementary material can be found at https://www.mauricequach.com/pcc_geo_cnn_samples