Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression

Maurice Quach
Frédéric Dufaux

Résumé

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 https://github.com/mauriceqch/pcc geo cnn.
Fichier principal
Vignette du fichier
2019_ICIP_Quach_et_al.pdf (1.62 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02116891 , version 1 (10-01-2020)

Identifiants

Citer

Maurice Quach, Giuseppe Valenzise, Frédéric Dufaux. Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. 26th IEEE International Conference on Image Processing (ICIP 2019), Sep 2019, Taipei, Taiwan. pp.4320-4324, ⟨10.1109/ICIP.2019.8803413⟩. ⟨hal-02116891⟩
115 Consultations
94 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More