Deformable Pose Network: A Multi-Stage Deformable Convolutional Network for 2D Hand Pose Estimation

Sartaj Salman, Ali Zakir, Hiroki Takahashi, Hiroki Takahashi

2024

Abstract

Hand pose estimation undergoes a significant advancement with the evolution of Convolutional Neural Networks (CNNs) in the field of computer vision. However, existing CNNs fail in many scenarios in learning the unknown transformations and geometrical constraints along with the other existing challenges for accurate estimation of hand keypoints. To tackle these issues we proposed a multi-stage deformable convolutional network for accurate 2D hand pose estimation from monocular RGB images while considering the computational complexity. We utilized EfficientNet as a backbone due to its powerful feature extraction capability, and deformable convolution to learn about the geometrical constraints. Our proposed model called Deformable Pose Network (DPN) outperforms in predicting the 2D keypoints in complex scenarios. Our analysis on the Panoptic studio hand dataset shows that our proposed model improves the accuracy by 2.36% and 7.29% as compared to existing methods i.e., OCPM and CPM respectively.

Paper Citation

in Harvard Style

Salman S., Zakir A. and Takahashi H. (2024). Deformable Pose Network: A Multi-Stage Deformable Convolutional Network for 2D Hand Pose Estimation. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 814-821. DOI: 10.5220/0012569000003660

in Bibtex Style

@conference{visapp24,
author={Sartaj Salman and Ali Zakir and Hiroki Takahashi},
title={Deformable Pose Network: A Multi-Stage Deformable Convolutional Network for 2D Hand Pose Estimation},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={814-821},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012569000003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Deformable Pose Network: A Multi-Stage Deformable Convolutional Network for 2D Hand Pose Estimation
SN - 978-989-758-679-8
AU - Salman S.
AU - Zakir A.
AU - Takahashi H.
PY - 2024
SP - 814
EP - 821
DO - 10.5220/0012569000003660
PB - SciTePress