Learning Non-Rigid 3D Shape from 2D Motion
Abstract
This paper presents an algorithm for learning the time-varying shape of a non-rigid 3D object from uncalibrated 2D tracking data. We model shape motion as a rigid component (rotation and translation) combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deforma- tions are allowed. We constrain the problem by assuming that the object shape at each time instant is drawn from a Gaussian distribution. Based on this assumption, the algorithm simultaneously estimates 3D shape and motion for each time frame, learns the parameters of the Gaussian, and robustly fills-in missing data points. We then extend the algorithm to model temporal smoothness in object shape, thus allowing it to handle severe cases of missing data.
Cite
Text
Torresani et al. "Learning Non-Rigid 3D Shape from 2D Motion." Neural Information Processing Systems, 2003.Markdown
[Torresani et al. "Learning Non-Rigid 3D Shape from 2D Motion." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/torresani2003neurips-learning/)BibTeX
@inproceedings{torresani2003neurips-learning,
title = {{Learning Non-Rigid 3D Shape from 2D Motion}},
author = {Torresani, Lorenzo and Hertzmann, Aaron and Bregler, Christoph},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {1555-1562},
url = {https://mlanthology.org/neurips/2003/torresani2003neurips-learning/}
}