Multiscale deep context modeling for lossless point cloud geometry compression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Multiscale deep context modeling for lossless point cloud geometry compression

Dat Thanh Nguyen
  • Fonction : Auteur
  • PersonId : 781952
  • IdRef : 199319111
Maurice Quach
Pierre Duhamel

Résumé

We propose a practical deep generative approach for lossless point cloud geometry compression, called MSVoxelDNN, and show that it significantly reduces the rate compared to the MPEG G-PCC codec. Our previous work based on autoregressive models (VoxelDNN [1]) has a fast training phase, however, inference is slow as the occupancy probabilities are predicted sequentially, voxel by voxel. In this work, we employ a multiscale architecture which models voxel occupancy in coarse-to-fine order. At each scale, MSVoxelDNN divides voxels into eight conditionally independent groups, thus requiring a single network evaluation per group instead of one per voxel. We evaluate the performance of MSVoxelDNN on a set of point clouds from Microsoft Voxelized Upper Bodies (MVUB) and MPEG, showing that the current method speeds up encoding/decoding times significantly compared to the previous VoxelDNN, while having average rate saving over G-PCC of 17.5%
Fichier principal
Vignette du fichier
Multiscale_deep_context_modelling_for_lossless_dense_point_cloud_compression.pdf (523.66 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03216378 , version 1 (04-05-2021)

Identifiants

Citer

Dat Thanh Nguyen, Maurice Quach, Giuseppe Valenzise, Pierre Duhamel. Multiscale deep context modeling for lossless point cloud geometry compression. IEEE International Conference on Multimedia & Expo Workshops (ICMEW), Jul 2021, Shenzhen (virtual), China. ⟨10.1109/ICMEW53276.2021.9455990⟩. ⟨hal-03216378⟩
100 Consultations
57 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More