A Non-parametric Bayesian Network Prior of Human Pose

Andreas M. Lehrmann, Peter V. Gehler, Sebastian Nowozin; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 1281-1288

Abstract


Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows realtime scoring of poses.

Related Material


[pdf]
[bibtex]
@InProceedings{Lehrmann_2013_ICCV,
author = {Lehrmann, Andreas M. and Gehler, Peter V. and Nowozin, Sebastian},
title = {A Non-parametric Bayesian Network Prior of Human Pose},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}