Effects of Adaptive Streaming Optimizations on the Perception of 360° Virtual Reality Video

Abstract

As the demand of Virtual Reality (VR) video streaming to mobile devices increases, novel optimization transport techniques need to be designed to cope with these ultra-highbandwidth video services. One approach currently attracting attention is the application of adaptive tile-based streaming solutions to the VR video arena. The VR videos are encoded at different quality levels, temporally divided into segments and spatially split into tiles. During the streaming, each of these tiles can be transmitted independently according to its location within the frame (i.e., within or outside of the user's field of view). These methods open a new venue for bandwidth and latency optimization for the streaming of VR videos. However, the effect of the different adaptive streaming optimizations on the end-user perception is still an open research topic. In this demo, we present a VR video platform to experience the working principles of adaptive tile-based VR video streaming services. Through different tiling approaches, bandwidth conditions and viewport algorithms, it allows the users to explore the effects that each optimization has on the perception of the service. In addition, the platform provides real-time bandwidth savings and objective Quality of Experience (QoE) measurements to provide a quantitative analysis of the optimizations effects. This demo aims to provide a common playground for researchers to benchmark and evaluate the performance of their optimization solutions.

Contextual Bandit Learning-Based Viewport Prediction for 360 Video

“…A testbed was developed for the adaptive tile-based streaming use case of 360°video [1]. A mobile HMD is wirelessly connected to a VR content server that performs all predictions, stitching and encoding of the tiles before streaming the video to the HMD.…”

“…Prediction error only gives half of the view on the performance and effectiveness of using a bandit agent to predict viewing behavior for adaptive 360°video streaming. The quality of the video within 1 https://www.youtube.com/watch?v=G-XZhKqQAHU the viewport is the most interesting outcome. The bottom of Table 1 shows the average relative quality within the viewport over the entire video for each user.…”

[DC] Self-Adaptive Technologies for Immersive Trainings

“…Secondly, we have developed a testbed for adaptive streaming of VR video [3] which will allow to further research the streaming techniques for the VRET use case. The core of the adaptive streaming technologie is accurate viewpoint prediction which also is the focus of the the second challenge.…”