We present a system and techniques for synthesizing views for three dimensional video teleconferencing. Instead of performing complex 3D scene acquisition, we decided to trade storage/hardware for computation, i.e., using more cameras. While it is expensive to directly capture a scene from all possible viewpoints, we observed that the participants' viewpoints usually remain at a constant height (eye level) during video teleconferencing. Therefore we can restrict the possible viewpoint to be within a virtual plane without sacrificing much of the realism. Doing so signicantly reduces the number of cameras required. We demonstrate a realtime system that uses a linear array of cameras to perform Light-Field style rendering. The simplicity and robustness of light fielding rendering, combined with the natural restrictions of limited view volume in video teleconferencing, allow us to synthesize photo-realistic views persuser request at interactive rate.
[1]
Takeo Kanade,et al.
Virtual Space Teleconferencing Using a Sea of Cameras
,
1994
.
[2]
Michael Bosse,et al.
Unstructured lumigraph rendering
,
2001,
SIGGRAPH.
[3]
Marc Levoy,et al.
Light field rendering
,
1996,
SIGGRAPH.
[4]
Zhengyou Zhang,et al.
A Flexible New Technique for Camera Calibration
,
2000,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
Anselmo Lastra,et al.
Creating Adaptive Views for Group Video Teleconferencing – An Image-Based Approach
,
2002
.
[6]
Greg Welch,et al.
The office of the future: a unified approach to image-based modeling and spatially immersive displays
,
1998,
SIGGRAPH.
[7]
William Buxton,et al.
Beating the limitations of camera-monitor mediated telepresence with extra eyes
,
1996,
CHI.