Dense 3D Motion Capture from Synchronized Video Streams
Abstract
This paper proposes a novel approach to non-rigid, markerless motion capture from synchronized video streams acquired by calibrated cameras. The instantaneous geometry of the observed scene is represented by a polyhedral mesh with fixed topology. The initial mesh is constructed in the first frame using the publicly available PMVS software for multi-view stereo [7]. Its deformation is captured by tracking its vertices over time, using two optimization processes at each frame: a local one using a rigid motion model in the neighborhood of each vertex, and a global one using a regularized nonrigid model for the whole mesh. Qualitative and quantitative experiments using seven real datasets show that our algorithm effectively handles complex nonrigid motions and severe occlusions.
Cite
Text
Furukawa and Ponce. "Dense 3D Motion Capture from Synchronized Video Streams." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587495Markdown
[Furukawa and Ponce. "Dense 3D Motion Capture from Synchronized Video Streams." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/furukawa2008cvpr-dense/) doi:10.1109/CVPR.2008.4587495BibTeX
@inproceedings{furukawa2008cvpr-dense,
title = {{Dense 3D Motion Capture from Synchronized Video Streams}},
author = {Furukawa, Yasutaka and Ponce, Jean},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2008},
doi = {10.1109/CVPR.2008.4587495},
url = {https://mlanthology.org/cvpr/2008/furukawa2008cvpr-dense/}
}