STEREOSCOPIC CONTENT PRODUCTION OF COMPLEX DYNAMIC SCENES USING A WIDE-BASELINE MONOSCOPIC CAMERA SET-UP

ICIP 2010 Special Session on Image Processing for Stereo Digital Cinema Production

Jean-Yves Guillemaut, Muhammad Sarim and Adrian Hilton
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK


Overview


Abstract

Conventional stereoscopic video content production requires use of dedicated stereo camera rigs which is both costly and lacking video editing flexibility. In this paper, we propose a novel approach which only requires a small number of standard cameras sparsely located around a scene to automatically convert the monocular inputs into stereoscopic streams. The approach combines a probabilistic spatio-temporal segmentation framework with a state-of-the-art multi-view graph-cut reconstruction algorithm, thus providing full control of the stereoscopic settings at render time. Results with studio sequences of complex human motion demonstrate the suitability of the method for high quality stereoscopic content generation with minimum user interaction.


Supplementary videos

All videos are encoded with the Windows Media Video 8 codec.

salsa - mesh salsa - mesh salsa - stereo
Monoscopic input
[Standard format (15MB)]
Reconstructed geometry
[Standard format (5MB)]
Stereoscopic output *
[Over-and-Under format (15MB)]
salsa - mesh salsa - mesh salsa - stereo
Monoscopic input
[Standard format (15MB)]
Reconstructed geometry
[Standard format (5.3MB)]
Stereoscopic output *
[Over-and-Under format (15MB)]

* Requires a stereoscopic player; free software for Windows can be downloaded from http://3dtv.at.