Content-Aware Adaptive Point Cloud Delivery
Key: AGM+22-1
Author: Yassin Alkhalili, Thomas Gruczyk, Tobias Meuser, Antonio Fernandez Anta, Ahmad Khalil, and Andreas Mauthe
Date: December 2022
Kind: In proceedings
Publisher: IEEE
Keywords: Point Cloud, Semantic Segmentation, Autonomous Vehicles, Virtual Reality
Abstract: Point clouds are an important enabler for a wide range of applications in various domains, including autonomous vehicles and virtual reality applications. Hence, the practical applicability of point clouds is gaining increasing importance and presenting new challenges for communication systems where large amounts of data need to be shared with low latency. Point cloud content can be very large, especially when multiple objects are involved in the scene. Major challenges of point clouds delivery are related to streaming in bandwidth-constrained networks and to resource-constrained devices. In this work, we are exploiting object-related knowledge, i.e., content-driven metrics, to improve the adaptability and efficiency of point clouds transmission. This study proposes applying a 3D point cloud semantic segmentation deep neural network and using objectrelated knowledge to assess the importance of each object in the scene. Using this information, we can semantically adapt the bit rate and utilize the available bandwidth more efficiently. The experimental results conducted on a real-world dataset showed that we can significantly reduce the requirement for multiple object point cloud transmission with limited quality degradation compared to the baseline without modifications.
View Full paper (PDF) | Download Full paper (PDF)

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.