Rate-adaptive streaming of 360-degree videos with head-motion-aware viewport margins

Abstract

Efficient use of available bandwidth is vital when streaming 360-degree videos as users rarely have enough bandwidth for a pleasant experience. A promising solution is the combination of viewport-dependent streaming using tiled video and rate adaptation, where the goal is to spend most of the available bandwidth for the viewport tiles. However, head motions resulting in a change in the viewport tiles briefly cause low-quality rendering until the new tiles can be replaced with high-quality versions. Previously, viewport margins-fixed regions around the viewport rendered at a medium quality-were proposed to make the viewport changes less abrupt. Later on, Head-motion-aware Viewport Margins (HMAVM) were implemented to further smooth the transitions at the expense of increased bandwidth consumption. In this paper, we manage the overall bandwidth cost of HMAVMs better by first developing a set of algorithms that trade off the quality of some viewport tiles and then making the margin selection part of the rate-adaptation algorithm.