Prometheus: A mobile telepresence system connecting the 1st person and 3rd person perspectives continuously

Abstract

Figure 1: System overview. A remote worker captures the area with a camera and streams the image (we call it rst-person view) to our system. Then, the system estimates the camera’s position and direction from the image and the pre-scanned 3D geometry. Finally, our system generates a third-person view by overlapping the captured image and the location information on the geometry. The receiver can switch these views freely. (a) First-person view: The image captured by remote worker is displayed in the center, with the pre-scanned geometry around it. This view moves with the movement of the remote worker. (b) Switching between rst-person and third-person view: The receiver can switch between the two views. (c) Third-person view: The user can move the viewpoint freely in the geometry model. The rst-person view and the camera’s position are also displayed so that the receiver can know the location of the remote worker.