Enhancing 3D Human Pose Estimation: A Novel Post-Processing Method

Elham Iravani, Elham Iravani, Frederik Hasecke, Lukas Hahn, Tobias Meisen

2025

Abstract

Human Pose Estimation (HPE) is a critical task in computer vision, involving the prediction of human body joint coordinates from images or videos. Traditional 3D HPE methods often predict joint positions relative to a central body part, such as the hip. Transformer-based models like PoseFormer (Zheng et al., 2021), MHFormer (Li et al., 2022b), and PoseFormerV2 (Zhao et al., 2023) have advanced the field by capturing spatial and temporal relationships to improve prediction accuracy. However, these models primarily output relative joint positions, requiring additional steps for absolute pose estimation. In this work, we present a novel post-processing technique that refines the output of other HPE methods from monocular images. By leveraging projection and spatial constraints, our method enhances the accuracy of relative joint predictions and seamlessly transitions them to absolute poses. Validated on the Human3.6M dataset (Ionescu et al., 2013), our approach demonstrates significant improvements over existing methods, achieving state-of-the-art performance in both relative and absolute 3D human pose estimation. Our method achieves a notable error reduction, with a 33.9% improvement compared to PoseFormer and a 27.2% improvement compared to MHFormer estimations.

Paper Citation

in Harvard Style

Iravani E., Hasecke F., Hahn L. and Meisen T. (2025). Enhancing 3D Human Pose Estimation: A Novel Post-Processing Method. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 209-220. DOI: 10.5220/0013316600003912

in Bibtex Style

@conference{visapp25,
author={Elham Iravani and Frederik Hasecke and Lukas Hahn and Tobias Meisen},
title={Enhancing 3D Human Pose Estimation: A Novel Post-Processing Method},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={209-220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013316600003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Enhancing 3D Human Pose Estimation: A Novel Post-Processing Method
SN - 978-989-758-728-3
AU - Iravani E.
AU - Hasecke F.
AU - Hahn L.
AU - Meisen T.
PY - 2025
SP - 209
EP - 220
DO - 10.5220/0013316600003912
PB - SciTePress