Bringing 3D Vision to the Web: Acquiring Motion Parallax using Commodity Cameras and WebGL

Abstract

In this paper, we present a system to acquire 3D vision by motion parallax on web-based platforms using head tracking. We employ the camshift algorithm to perform color-based head tracking. Using the position of the head, we can render a 3D scene from the viewpoint of the viewer, thus acquiring motion parallax, a strong cue for 3D vision. We employed web technologies to allow the adoption of our method to any modern device, including mobile devices. WebGL is used for rendering and head tracking, andWebRTC is used for camera input. No software installation or plugins are required. We demonstrated the effectiveness of our method on a variety of devices, such as desktop computers, laptops, and tablets.