Metraipolis › archive › dc_ee68b0e65ef6

Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model — arXiv:2608.29928

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29928
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:14.271Z
SHA-256 of the archived text
387739f226b9f32bee4b3b3440114fab51064310fc667337e91f83fdad1c8e8b
Stable URL of this page
https://metraipolis.com/documento/dc_ee68b0e65ef6

How to cite

Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model — arXiv:2608.29928 — arXiv (en), https://arxiv.org/abs/2608.29928 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee68b0e65ef6 (Metraipolis archive dc_ee68b0e65ef6, sha256 387739f226b9f32bee4b3b3440114fab51064310fc667337e91f83fdad1c8e8b)
BibTeX
@misc{dcee68b0e65ef6,
  title = {Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model — arXiv:2608.29928},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29928},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee68b0e65ef6; sha256 387739f226b9f32bee4b3b3440114fab51064310fc667337e91f83fdad1c8e8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29928. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechanically defined joint angles that downstream applications like clinical and biomechanical analyses require. We extend an existing foundation model, SAM-3D-Body, with an additional biomechanical prediction head that, from a single RGB image, regresses the joint angles and scales of a biomechanical model. Training this model presents a challenge, as there are limited datasets of paired images and biomechanical fits. To overcome this, we supervise biomechanical outputs with in-loop optimized targets from a Levenberg-Marquardt solver performing inverse kinematics fits against markers from the mesh predictions. This allows distilling the biomechanical head from the mesh head, even from unlabeled images. To make this work with GPU-optimized biomechanical models in MuJoCo, the entire model was implemented in JAX using Equinox. We trained this distilled output head on the publicly released SAM-3D-Body dataset. We then validated this model on biomechanical fits to two publicly available marker-based datasets, MoVi and BioCV, as well as movements from a clinical cohort captured with multiview markerless motion capture. The resulting model outperforms existing models for direct regression of biomechanics from images while only slightly underperforming the state-of-the-art monocular biomechanics method that performs more costly inference-time optimization of entire trajectories.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29928 — 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 2026-10-17T09:28:48.091Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).