Rethinking the Sparse End-to-End Multiperson Pose Estimation
IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2025-04 · 55 (4) · 2388-2398
DOI: 10.1109/tsmc.2024.3525021 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2025-04. Verfasst von Xixia Xu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Shanghai Natural Science Foundation, Postdoctoral Fellowship Program (Grade C) of China Postdoctoral Science Foundation, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Current methods of multiperson pose estimation (MPPE) typically treat the human detection and association of joints separately. They introduce complex hand-crafted pose-processes like RoI cropping, NMS and grouping or rely on dense representations to preserve the spatial features. In this article, we dive a deeper thought into this task and propose a simpler and effective framework, termed SparsePose, which can directly predict multiperson joint coordinates from the full image without any post-processes and dense representations. In SparsePose, the full-body instances are decoupled by exploring spatial-aware feature learning (SFL) without box and classification supervision. For improving the quality of instance map, the instance contrastive constraint (ICC) and center correction (CC) strategy are proposed to make the instance-wise spatial feature more discriminative. Importantly, we propose a visibility-guided weighting mechanism to enable model be confident to the visible joint predictions and insensitive to the occlusions or partial bodies. In general, SparsePose is conceptually simpler and plays favorably against the existing counterparts on three benchmarks in terms of both accuracy and efficiency.
Förderung
- Shanghai Natural Science Foundation
- Postdoctoral Fellowship Program (Grade C) of China Postdoctoral Science Foundation
- Beijing Natural Science Foundation
- Natural Science Foundation of Hebei Province
- Program of Shanghai Academic Research Leader
Zitieren
APA
Xu, X., Zou, Q., & Li, J. (2025). Rethinking the Sparse End-to-End Multiperson Pose Estimation. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 55(4), 2388-2398. https://doi.org/10.1109/tsmc.2024.3525021
Vancouver
Xu X, Zou Q, Li J. Rethinking the Sparse End-to-End Multiperson Pose Estimation. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025;55(4):2388-2398. doi:10.1109/tsmc.2024.3525021
BibTeX
@article{Xu2025,
author = {Xu, Xixia and Zou, Qi and Li, Jiamao},
title = {Rethinking the Sparse End-to-End Multiperson Pose Estimation},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
year = {2025},
volume = {55},
number = {4},
pages = {2388--2398},
doi = {10.1109/tsmc.2024.3525021}
}
EUVIMED