Dynamic Load Distribution in web-based AR

Abstract

In a web-based Augmented Reality (AR) application, to achieve an immersive experience we require precise object detection, realistic model rendering, smooth occlusion, and accurate augmentation in real-time. To achieve these objectives on a device requires heavy computation capabilities unavailable on most mobile devices, this can be solved by using cloud computing but it introduces network latency issues. In this work, we propose a new network protocol named DLDAR (Dynamic Load Distribution in web-based AR) that facilitates and standardizes methods for dynamic division of compute between client and server for achieving real-time performance in a comprehensive AR web application. The protocol will manage computation and network latency by dynamically provisioning compute between client and server based on device and network condition to min-max latency and quality. We demonstrate our approach by developing a web application that enables users to celebrate the regional festival “Raksha Bandan” by sharing wristbands “rakhis” that can be augmented on your wrist. This protocol can be used to create complex web AR applications with more realistic rendering, animations, and interactive environments.