Cloud Gaming With Foveated Graphics

TL;DR

This paper presents a system for cloud gaming that uses foveated video encoding to significantly reduce bandwidth requirements by leveraging human visual acuity and eye tracking, while maintaining user experience.

Contribution

The authors designed and implemented a real-time foveated graphics system for cloud gaming using consumer eye trackers and evaluated its performance and user perception.

Findings

Bandwidth savings of up to 50% with minimal user notice

Identification of optimal encoding parameters for user experience

Feasibility demonstrated with diverse game genres

Abstract

Cloud gaming enables playing high end games, originally designed for PC or game console setups, on low end devices, such as net-books and smartphones, by offloading graphics rendering to GPU powered cloud servers. However, transmitting the high end graphics requires a large amount of available network bandwidth, even though it is a compressed video stream. Foveated video encoding (FVE) reduces the bandwidth requirement by taking advantage of the non-uniform acuity of human visual system and by knowing where the user is looking. We have designed and implemented a system for cloud gaming with foveated graphics using a consumer grade real-time eye tracker and an open source cloud gaming platform. In this article, we describe the system and its evaluation through measurements with representative games from different genres to understand the effect of parameterization of the FVE scheme on bandwidth requirements and to understand its feasibility from the latency perspective. We also present results from a user study. The results suggest that it is possible to find a "sweet spot" for the encoding parameters so that the users hardly notice the presence of foveated encoding but at the same time the scheme yields most of the bandwidth savings achievable.