(TIP24) Approaching unrestricted and full rotation head pose estimation!
We are delighted to share our newest publication in the IEEE Transaction on Image Processing. In this paper, we tackle the major challenge of unconstrained full rotation head pose estimation that is a rarely explored research subject yet.
New head pose method presented in IEEE Transaction on Image Processing
In this paper, we introduce a novel method for unconstrained end-to-end head pose estimation, aiming to accurately predict a full range of head orientations beyond the limitations of traditional frontal pose prediction approaches. By employing a continuous 6D rotation matrix representation, our method enables efficient learning of full rotation appearance, enhancing the robustness and efficiency of direct regression. The approach, supported by new accumulated training data and a geodesic loss mechanism, significantly surpasses existing state-of-the-art methods in terms of efficiency and accuracy across public datasets. Check out the codebase at https://github.com/thohemp/6DRepNet360.
Fulltext Access
https://ieeexplore.ieee.org/document/10477888
Citing
@ARTICLE{10477888,
author={Hempel, Thorsten and Abdelrahman, Ahmed A. and Al-Hamadi, Ayoub},
journal={IEEE Transactions on Image Processing},
title={Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation},
year={2024},
volume={},
number={},
pages={1-1},
keywords={head pose estimation;full range of rotation;rotation matrix;6D representation;geodesic loss},
doi={10.1109/TIP.2024.3378180}}