Metraipolis › archive › dc_56e371d8a643
ArmPoser: Real-Time, Calibration-Free Arm Pose Estimation from Smartwatch IMU — arXiv:2609.08806
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08806
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:46:54.926Z
- SHA-256 of the archived text
c62342eac21cb278821cec15000b43f43a92a415e9992c2e91b0a4d5d16505dc- Stable URL of this page
https://metraipolis.com/documento/dc_56e371d8a643
How to cite
ArmPoser: Real-Time, Calibration-Free Arm Pose Estimation from Smartwatch IMU — arXiv:2609.08806 — arXiv (en), https://arxiv.org/abs/2609.08806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56e371d8a643 (Metraipolis archive dc_56e371d8a643, sha256 c62342eac21cb278821cec15000b43f43a92a415e9992c2e91b0a4d5d16505dc)
BibTeX
@misc{dc56e371d8a643,
title = {ArmPoser: Real-Time, Calibration-Free Arm Pose Estimation from Smartwatch IMU — arXiv:2609.08806},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08806},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56e371d8a643; sha256 c62342eac21cb278821cec15000b43f43a92a415e9992c2e91b0a4d5d16505dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Arm pose estimation enables applications in fitness, extended reality input, rehabilitation, and life logging. Prior smartwatch-based approaches rely on calibration poses and preprocessing pipelines that transform raw IMU measurements into standardized training formats. These steps hinder deployment in everyday settings and introduce errors due to imperfect calibration and sensor drift. We present ArmPoser, a calibration-free arm pose estimation system using a single smartwatch IMU. Our central contribution is training models directly in the reference frame native to consumer smartwatches, aligning learning with how IMU data is produced by deployed devices. By operating on device-native axes, ArmPoser removes the need for coordinate transformations, explicit alignment, and bone-offset calibration used in prior work. We further augment training with physically grounded variations in watch placement and arm morphology to account for user-specific variability. ArmPoser also includes a wear-configuration module that infers anterior or posterior forearm placement and crown orientation. We evaluate pose estimation on public benchmarks and on a 10-participant, 30-activity study using watchOS and Android smartwatches, where ArmPoser matches or exceeds calibrated baselines without any user calibration. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.HC). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.08806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:28:43.175Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).