Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation

Abstract

Estimating 3D pose from monocular images is a highly ambiguous problem. Physical constraints can be exploited to restrict the space of feasible configurations. In this paper we propose an approach to constraining the prediction of a discriminative predictor. We first show that the mean prediction of a Gaussian process implicitly satisfies linear constraints if those constraints are satisfied by the training examples. We then show how, by performing a change of variables, a GP can be forced to satisfy quadratic constraints. As evidenced by the experiments, our method outperforms state-of-the-art approaches on the tasks of rigid and non-rigid pose estimation.

Cite

Text

Salzmann and Urtasun. "Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation." Neural Information Processing Systems, 2010.

Markdown

[Salzmann and Urtasun. "Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/salzmann2010neurips-implicitly/)

BibTeX

@inproceedings{salzmann2010neurips-implicitly,
  title     = {{Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation}},
  author    = {Salzmann, Mathieu and Urtasun, Raquel},
  booktitle = {Neural Information Processing Systems},
  year      = {2010},
  pages     = {2065-2073},
  url       = {https://mlanthology.org/neurips/2010/salzmann2010neurips-implicitly/}
}