Low-latency Cloud-based Volumetric Video Streaming Using Head Motion Prediction

October 29, 2020 – /,

As a developing media content, point cloud has gained great interests in both industry and research due to its applicability in diverse areas such as virtual reality, autonomous driving, and video gaming.
High-quality 3D point cloud would enable new ways of interaction with the virtual environments. However, point clouds are highly resource-demanding and therefore are difficult to stream at an acceptable quality level especially for mobile devices. An Edge/cloud server can be used to do the heavy rendering operations in order to decrease the computational overhead at the client side. However, this solution increases the overall streaming latency.  
In this work, the student will investigate employing a head/pose motion prediction model to the reduce the motion-to-photon latency.

download corresponding tendering


Research Area(s):

Tutor: Alkhalili,

Open Theses