Model-Based Deep Hand Pose Estimation
Abstract
Previous learning based hand pose estimation methods does not fully exploit the prior information in hand model geometry. Instead, they usually rely a separate model fitting step to generate valid hand poses. Such a post processing is inconvenient and sub-optimal. In this work, we propose a model based deep learning approach that adopts a forward kinematics based layer to ensure the geometric validity of estimated poses. For the first time, we show that embedding such a non-linear generative process in deep learning is feasible for hand pose estimation. Our approach is verified on challenging public datasets and achieves state-of-the-art performance. PDF
Cite
Text
Zhou et al. "Model-Based Deep Hand Pose Estimation." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Zhou et al. "Model-Based Deep Hand Pose Estimation." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/zhou2016ijcai-model/)BibTeX
@inproceedings{zhou2016ijcai-model,
title = {{Model-Based Deep Hand Pose Estimation}},
author = {Zhou, Xingyi and Wan, Qingfu and Zhang, Wei and Xue, Xiangyang and Wei, Yichen},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {2421-2427},
url = {https://mlanthology.org/ijcai/2016/zhou2016ijcai-model/}
}