Salam Khalifa and Naveed Ahmed
Temporally Coherent 3D Animation Reconstruction from RGBD Video Data
1483 - 1489
2014
8
8
International Journal of Computer and Information Engineering
https://publications.waset.org/pdf/9999406
https://publications.waset.org/vol/92
World Academy of Science, Engineering and Technology
We present a new method to reconstruct a temporally
coherent 3D animation from single or multiview RGBD video data
using unbiased feature point sampling. Given RGBD video data, in
form of a 3D point cloud sequence, our method first extracts feature
points using both color and depth information. In the subsequent
steps, these feature points are used to match two 3D point clouds in
consecutive frames independent of their resolution. Our new motion
vectors based dynamic alignement method then fully reconstruct
a spatiotemporally coherent 3D animation. We perform extensive
quantitative validation using novel error functions to analyze the
results. We show that despite the limiting factors of temporal and
spatial noise associated to RGBD data, it is possible to extract
temporal coherence to faithfully reconstruct a temporally coherent
3D animation from RGBD video data.
Open Science Index 92, 2014