We present a methodology to develop a low-cost, low-bandwidth visual telepresence system using commodity depth sensors. To obtain a precise representation of the participants, we fuse together multiple views extracted… Click to show full abstract
We present a methodology to develop a low-cost, low-bandwidth visual telepresence system using commodity depth sensors. To obtain a precise representation of the participants, we fuse together multiple views extracted using a deep background subtraction method. We build a proof-of-concept display composed of a video projector and a quadrangular pyramid made of acrylic, to demonstrate the visualization of a remote person without the need for head-mounted displays. Our system represents an attempt to democratize high-fidelity 3D telepresence using off-the-shelf components.
               
Click one of the above tabs to view related content.