Learning Joint Twist Rotation for 3D Human Pose Estimation from a Single Image

Chihiro Nakatsuka, Jianfeng Xu, Kazuyuki Tasaka

2021

Abstract

We consider monocular 3D human pose estimation with joint rotation representations because they are more expressive than joint location representations and better suited to some applications such as CG character control and human motion analysis in sports or surveillance. Previous approaches have encountered difficulties when estimating joint rotations with actual twist rotation around limbs. We present a novel approach to estimating joint rotations with actual twist rotations from a single image by handling joint rotations separately decomposed into swing and twist rotations. To extract twist rotations from an image, we emphasize the joint appearances and use them effectively in our model. Our model estimates the twist angles with an average radian error of 0.14, and we show that estimation of twist rotations achieves a more precise 3D human pose.

Paper Citation

in Harvard Style

Nakatsuka C., Xu J. and Tasaka K. (2021). Learning Joint Twist Rotation for 3D Human Pose Estimation from a Single Image. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 379-386. DOI: 10.5220/0010222703790386

in Bibtex Style

@conference{visapp21,
author={Chihiro Nakatsuka and Jianfeng Xu and Kazuyuki Tasaka},
title={Learning Joint Twist Rotation for 3D Human Pose Estimation from a Single Image},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={379-386},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010222703790386},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Learning Joint Twist Rotation for 3D Human Pose Estimation from a Single Image
SN - 978-989-758-488-6
AU - Nakatsuka C.
AU - Xu J.
AU - Tasaka K.
PY - 2021
SP - 379
EP - 386
DO - 10.5220/0010222703790386
PB - SciTePress