Recovering 3D Human Poses and Camera Motions from Deep Sequence

Takashi Shimizu, Fumihiko Sakaue, Jun Sato

2018

Abstract

In this paper, we propose a novel method for recovering 3D human poses and camera motions from sequential images by using CNN and LSTM. The human pose estimation from deep learning has been studied extensively in recent years. However, the existing methods aim to classify 2D human motions in images. Although some methods have been proposed for recovering 3D human poses recently, they only considered single frame poses, and sequential properties of human actions were not used efficiently. Furthermore, the existing methods recover only 3D poses relative to the viewpoints. In this paper, we propose a method for recovering 3D human poses and 3D camera motions simultaneously from sequential input images. In our network, CNN is combined with LSTM, so that the proposed network can learn sequential properties of 3D human poses and camera motions efficiently. The efficiency of the proposed method is evaluated by using real images as well as synthetic images.

Paper Citation

in Harvard Style

Shimizu T., Sakaue F. and Sato J. (2018). Recovering 3D Human Poses and Camera Motions from Deep Sequence. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 393-398. DOI: 10.5220/0006718603930398

in Bibtex Style

@conference{visapp18,
author={Takashi Shimizu and Fumihiko Sakaue and Jun Sato},
title={Recovering 3D Human Poses and Camera Motions from Deep Sequence},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={393-398},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006718603930398},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Recovering 3D Human Poses and Camera Motions from Deep Sequence
SN - 978-989-758-290-5
AU - Shimizu T.
AU - Sakaue F.
AU - Sato J.
PY - 2018
SP - 393
EP - 398
DO - 10.5220/0006718603930398
PB - SciTePress