Variable Rate Compression for Raw 3D Point Clouds

In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data. Moreover, many existing techniques require training multiple networ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 International Conference on Robotics and Automation (ICRA) S. 8748 - 8755
Hauptverfasser: Al Muzaddid, Md Ahmed, Beksi, William J.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 23.05.2022
Schlagworte:
Automation
Big Data in Robotics and Automation
Bit rate
Computational modeling
Deep Learning for Visual Perception
Point cloud compression
RGB-D Perception
Three-dimensional displays
Training
Visualization
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data. Moreover, many existing techniques require training multiple networks for different compression rates to generate consolidated point clouds of varying quality. In contrast, our network is capable of explicitly processing point clouds and generating a compressed description at a comprehensive range of bitrates. Furthermore, our approach ensures that there is no loss of information as a result of the voxelization process and the density of the point cloud does not affect the encoder/decoder performance. An extensive experimental evaluation shows that our model obtains state-of-the-art results, it is computationally efficient, and it can work directly with point cloud data thus avoiding an expensive voxelized representation.
DOI:10.1109/ICRA46639.2022.9812239