[AI-3DGC] NF-PCAC - deep point cloud attribute compression with normalizing flow - Archive ouverte HAL Accéder directement au contenu
Autre Publication Scientifique Année : 2022

[AI-3DGC] NF-PCAC - deep point cloud attribute compression with normalizing flow

Résumé

There exist different learning-based approaches to compress the geometry of point clouds, on the other hand the compression of attributes has been less explored. In this contribution we present a first normalizing flow architecture to compress point cloud attributes and the strategies to enable its use. The proposed method outperforms all other learning-based methods for point cloud attributes in the proposed quantitative measurement and has comparable results to G-PCC version 14 on some test models.
Fichier non déposé

Dates et versions

hal-04505886 , version 1 (15-03-2024)

Identifiants

  • HAL Id : hal-04505886 , version 1

Citer

Rodrigo Borba Pinheiro, Jean-Eudes Marvie, Giuseppe Valenzise, Frédéric Dufaux. [AI-3DGC] NF-PCAC - deep point cloud attribute compression with normalizing flow. ISO/IEC JTC 1/SC 29/WG7, m61142, 2022. ⟨hal-04505886⟩
1 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More