Improved Deep Point Cloud Geometry Compression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Improved Deep Point Cloud Geometry Compression

Maurice Quach
Frédéric Dufaux

Résumé

Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In addition, we present an extensive ablation study on the impact of each of these factors, in order to provide a better understanding about why they improve RD performance. An optimal combination of the proposed improvements achieves BD-PSNR gains over G-PCC trisoup and octree of 5.50 (6.48) dB and 6.84 (5.95) dB, respectively, when using the point-to-point (point-to-plane) metric. Code is available at https://github.com/mauriceqch/pcc_geo_cnn_v2.
Fichier principal
Vignette du fichier
2020_MMSP_Quach_et_al.pdf (489.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02910180 , version 1 (14-08-2020)

Identifiants

Citer

Maurice Quach, Giuseppe Valenzise, Frédéric Dufaux. Improved Deep Point Cloud Geometry Compression. IEEE International Workshop on Multimedia Signal Processing (MMSP'2020), Sep 2020, Tampere, Finland. pp.1-6, ⟨10.1109/MMSP48831.2020.9287077⟩. ⟨hal-02910180⟩
111 Consultations
357 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More