VCF-Pose: Velocity-Guided Coarse-to-Fine Pose Estimation From mmWave Point Clouds
IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 8198-8210
DOI: 10.1109/tccn.2026.3693281 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Xiaokai Liu und 4 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Liaoning Province, Science and Technology Program of Liaoning Province.
Abstract (Originalsprache)
Human pose estimation with millimeter-wave radar has become a promising alternative sensing method due to its robustness against varying lighting conditions and occlusions. However, existing methods often suffer from temporal inconsistencies and spatial inaccuracies, primarily due to the sparse nature of point clouds and the underutilization of valuable Doppler velocity information. To address this challenge, we propose VCF-Pose, a novel Velocity-guided Coarse-to-Fine Pose estimation framework that creatively transforms unstructured Doppler data into a structured motion representation to dynamically guide the refinement of an initial coarse pose, ensuring it aligns with temporal dynamics and anatomical priors. Specifically, VCF-Pose first generates an initial coarse pose estimate using a GRU-based sequential model to capture temporal context from voxelized radar data. Then we design a velocity space projection module that creatively transforms unstructured raw Doppler data into a structured 3D velocity feature volume. This novel representation enables a 3D relational convolution network to effectively model the fine-grained correlations between motion dynamics and spatial geometry. Finally, a structural prior-guided feature fusion module leverages anatomical constraints to perform global alignment and refinement, ensuring the final pose is anatomically plausible. Extensive experiments demonstrate that VCF-Pose significantly improves inter-frame continuity and reduces estimation error, achieving an average error of 4.03 cm and outperforming existing state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Liaoning Province
- Science and Technology Program of Liaoning Province
- Liaoning Revitalization Talents Program
- Dalian Science and Technology Innovation Fund
- Fundamental Research Funds for the Central Universities
- China Postdoctoral Science Foundation
- Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
Zitieren
APA
Liu, X., Qiao, L., Ji, Z., Wang, Y., & Wang, J. (2026). VCF-Pose: Velocity-Guided Coarse-to-Fine Pose Estimation From mmWave Point Clouds. IEEE Transactions on Cognitive Communications and Networking, 12, 8198-8210. https://doi.org/10.1109/tccn.2026.3693281
Vancouver
Liu X, Qiao L, Ji Z, Wang Y, Wang J. VCF-Pose: Velocity-Guided Coarse-to-Fine Pose Estimation From mmWave Point Clouds. IEEE Transactions on Cognitive Communications and Networking. 2026;12:8198-8210. doi:10.1109/tccn.2026.3693281
BibTeX
@article{Liu2026,
author = {Liu, Xiaokai and Qiao, Lihao and Ji, Zhiyong and Wang, Yangyang and Wang, Jie},
title = {VCF-Pose: Velocity-Guided Coarse-to-Fine Pose Estimation From mmWave Point Clouds},
journal = {IEEE Transactions on Cognitive Communications and Networking},
year = {2026},
volume = {12},
pages = {8198--8210},
doi = {10.1109/tccn.2026.3693281}
}
EUVIMED