Abstract—We present a system for spatio-temporally
coherent 3D animation reconstruction from multi-view RGB-D
images. Our system captures multi-view synchronous RGB-D
images from six RGB-D cameras and we show that by using the
unique properties of both depth and color images, it is possible
to reconstruct a spatio-temporally consistent 3D animation
from a non-coherent time-varying data. The reconstructed
spatio-temporally coherent 3D animation can be used in a
number of applications that require time-coherent data, e.g.
motion analysis, gesture recognition, compression,
free-viewpoint video and CG animations.
Index Terms—Multi-view video acquisition, 3D and
free-viewpoint video, dynamic scene reconstruction, RGB-D
data acquisition.
The authors are with University of Sharjah, United Arab Emirates
(e-mail: nahmed@sharjah.ac.ae, ijunejo@sharjah.ac.ae).
[PDF]
Cite:Naveed Ahmed and Imran Junejo, "Using Multiple RGB-D Cameras for 3D Video Acquisition and Spatio-Temporally Coherent 3D Animation Reconstruction," International Journal of Computer Theory and Engineering vol. 6, no. 6, pp. 447-450, 2014.
