Metraipolis › archive › dc_c8abb06e786d

Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds — arXiv:2608.03637

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03637
License (as archived): CC0-1.0
Archived: 2026-10-31T12:59:44.216Z
SHA-256 of the archived text: 8e29974354be8ae3c1a86a85042c664569d8bf09d3a53f057faac3fb8e17469c
Stable URL of this page: https://metraipolis.com/documento/dc_c8abb06e786d

How to cite

Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds — arXiv:2608.03637 — arXiv (en), https://arxiv.org/abs/2608.03637 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8abb06e786d (Metraipolis archive dc_c8abb06e786d, sha256 8e29974354be8ae3c1a86a85042c664569d8bf09d3a53f057faac3fb8e17469c)

BibTeX

@misc{dcc8abb06e786d,
  title = {Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds — arXiv:2608.03637},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03637},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8abb06e786d; sha256 8e29974354be8ae3c1a86a85042c664569d8bf09d3a53f057faac3fb8e17469c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03637. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Radar-based human pose estimation has focused on improving learning algorithms while representing the body as unconstrained keypoint coordinates. We address the underexplored dimension of anatomical fidelity by integrating a full-body skeletal model into a differentiable, end-to-end trainable radar-based pose estimation framework, in which the pose network is supervised through forward kinematics while subject-specific geometry is fitted beforehand. Subject-specific body segment proportions are predicted from radar point cloud features to scale a biomechanical skeleton. A motion prediction network maps temporal radar sequences to generalized coordinates, and differentiable forward kinematics converts predicted joint angles into 3D positions. A contact classification loss encourages physically plausible foot-ground interaction. Under leave-one-subject-out cross-validation on 11 healthy participants performing rehabilitation exercises, the framework achieves 6.456 +/- 1.759 cm mean per-joint position error (MPJPE), 8.083 +/- 0.884 degrees mean per-joint angle error (MPJAE), 0.935 +/- 0.009 contact classification F1, and 3.4 +/- 1.3 % scaling error. This proof-of-concept study demonstrates the feasibility of recovering interpretable biomechanical descriptors from a single low-cost radar sensor in a controlled laboratory setting, a prerequisite for future clinical motion analysis.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03637 — 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 2026-10-31T12:45:33.265Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).