A Direct Approach for Efficiently Tracking with 3D Morphable Models
Abstract
We present an efficient algorithm for fitting a morphable model to an image sequence. It is built on a projective geometry formulation of perspective projection, which results in a linear mapping from 3D shape to the projective plane, and a factorisation of this mapping into matrices that can be partially computed off-line. This algorithm can cope with full 360 degrees object rotation and linear deformations. We validate our approach using synthetically generated and real sequences. Compared to a plain Lucas-Kanade implementation, we achieve a six fold increase in performance for a rigid object and two fold for a non-rigid face.
Cite
Text
Muñoz et al. "A Direct Approach for Efficiently Tracking with 3D Morphable Models." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459366Markdown
[Muñoz et al. "A Direct Approach for Efficiently Tracking with 3D Morphable Models." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/munoz2009iccv-direct/) doi:10.1109/ICCV.2009.5459366BibTeX
@inproceedings{munoz2009iccv-direct,
title = {{A Direct Approach for Efficiently Tracking with 3D Morphable Models}},
author = {Muñoz, Enrique and Buenaposada, José Miguel and Baumela, Luis},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2009},
pages = {1615-1622},
doi = {10.1109/ICCV.2009.5459366},
url = {https://mlanthology.org/iccv/2009/munoz2009iccv-direct/}
}