Skip to Main content Skip to Navigation
Conference papers

Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression

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 Vox-elized 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 geo cnn.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download
Contributor : Frédéric Dufaux <>
Submitted on : Friday, January 10, 2020 - 11:27:47 AM
Last modification on : Wednesday, April 29, 2020 - 12:44:09 PM
Document(s) archivé(s) le : Saturday, April 11, 2020 - 2:39:24 PM


Files produced by the author(s)


  • HAL Id : hal-02116891, version 1


Maurice Quach, Giuseppe Valenzise, Frédéric Dufaux. Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. IEEE International Conference on Image Processing (ICIP’2019), Sep 2019, Taipei, Taiwan. ⟨hal-02116891⟩



Record views


Files downloads