Voxel-based Deep Point Cloud Geometry Compression

Giuseppe Valenzise (1) , Maurice Quach (1) , Dat-Than Nguyen (1) , Frédéric Dufaux (1)

1 L2S - Laboratoire des signaux et systèmes

We present two learning-based methods for coding point clouds geometry. The two methods target lossy and lossless compression, respectively, and have in common the fact to use a voxel-based representation of geometry. This representation enables us to extend well-known architectures used for 2D image generation and compression to 3D. We show that, when the point cloud density is sufficiently high, the voxel-based approach achieves state-of-the-art performance compared to conventional octree-based methods such as MPEG G-PCC.

Mots clés: point cloud; geometry coding; voxels; auto-encoder; generative models

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Giuseppe Valenzise, Maurice Quach, Dat-Than Nguyen, Frédéric Dufaux. Voxel-based Deep Point Cloud Geometry Compression. CORESA (COmpression et REprésentation des Signaux Audiovisuels), Nov 2021, Sophia-Antipolis, France. ⟨hal-03438488⟩