Metraipolis › archive › dc_552bcc7f96d7
Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation — arXiv:2609.01840
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01840
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:45.211Z
- SHA-256 of the archived text
96190ea492be58520c481d2774c72b806749edc99284363382f966948b00ac81- Stable URL of this page
https://metraipolis.com/documento/dc_552bcc7f96d7
How to cite
Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation — arXiv:2609.01840 — arXiv (en), https://arxiv.org/abs/2609.01840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_552bcc7f96d7 (Metraipolis archive dc_552bcc7f96d7, sha256 96190ea492be58520c481d2774c72b806749edc99284363382f966948b00ac81)
BibTeX
@misc{dc552bcc7f96d7,
title = {Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation — arXiv:2609.01840},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01840},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_552bcc7f96d7; sha256 96190ea492be58520c481d2774c72b806749edc99284363382f966948b00ac81},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spontaneous movement is one of the earliest windows onto an infant's neuromotor health, and structured clinical instruments that score it are validated early predictors of cerebral-palsy risk. However, they require specially trained raters, are time-consuming, and carry inter-rater variability. This motivates automated, video-based markerless assessment, especially as marker-based motion capture is impractical in infants. Yet the foundation models that make markerless capture possible are trained almost entirely on adults: our recent multi-view infant study found that no single model is jointly best, with strong 2D keypoint accuracy and direct 3D body recovery split across different models. While that study identifies this trade-off, it does not resolve it. Here, we perform cross-model distillation from the Sapiens 2 pose model into the SAM 3D Body model, using unannotated infant video alone. A frozen teacher supplies dense pseudo-labels, and a differentiable renderer aligns the predicted mesh to them in the training loop. On eleven held-out infants (18 sessions, 173 recordings) under our prior study's multi-view protocol, fine-tuning improves same-view 2D keypoint agreement with the Sapiens reference (median body percentage of correct keypoints @ 10px 0.22 -> 0.42, face 0.22 -> 0.42) and Procrustes-aligned mean per joint 3D position error (25.5 -> 22.2 mm). This demonstrates how cross-model distillation improves SAM 3D Body model performance on infants. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01840 — 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 2026-10-17T05:25:58.033Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).