Demo: Landscape: Saliency and Trajectory based Viewport Prediction in Point Cloud Video Streaming

Jie Li, Zhixin Li, Qiyue Li, Wei Sun, Weitao Li, Huiyu Wang, Zhi Liu

Abstract: Efficient point cloud video streaming requires accurate viewport prediction, and research on this topic is still in its infancy. This paper demonstrates a high-precision scheme for viewport prediction in the point cloud video, named Landscape, exploring both video saliency information and viewport trajectory. Specifically, we first propose a novel point cloud video sampling method, which reduces computational load while preserving video features. Furthermore, we introduce a new saliency detection technique that integrates temporal and spatial information to detect dynamic, static geometric, and color salient regions. Finally, we intelligently fuse saliency and trajectory information to achieve more accurate viewport prediction. We verify the performance of our proposed viewport prediction methods over state-of-the-art wireless networks.