Metraipolis › archive › dc_aaad4655adef

Everybody Tracking Every Body — arXiv:2608.29927

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29927
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:13.766Z
SHA-256 of the archived text
3c47eba1f2b2fc14e7aba0e6b0243abeb52b18bbbcf0c8a8d37470c5b7ab0a50
Stable URL of this page
https://metraipolis.com/documento/dc_aaad4655adef

How to cite

Everybody Tracking Every Body — arXiv:2608.29927 — arXiv (en), https://arxiv.org/abs/2608.29927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aaad4655adef (Metraipolis archive dc_aaad4655adef, sha256 3c47eba1f2b2fc14e7aba0e6b0243abeb52b18bbbcf0c8a8d37470c5b7ab0a50)
BibTeX
@misc{dcaaad4655adef,
  title = {Everybody Tracking Every Body — arXiv:2608.29927},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29927},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aaad4655adef; sha256 3c47eba1f2b2fc14e7aba0e6b0243abeb52b18bbbcf0c8a8d37470c5b7ab0a50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We address the problem of 3D body pose estimation of multiple interacting people from their egocentric views with centralized coordination. Each individual wears a camera recording egocentric video and IMU data. Processing this video with VIO SLAM provides high-quality tracking of each egocentric camera through space. The first-person view from one individual provides third-person observations of other people, although these exocentric observations are sparse, intermittent, and of highly variable reliability as both cameras and subjects move. To integrate these synchronized data streams, we propose a diffusion-based approach that fuses estimates of pose based on head motion derived from egocentric camera motion with exocentric pose observations, conditioning on both observation content and reliability. Our model is trained on a mixture of single-person motion-capture data and multi-person video in order to learn rich priors for body motion trajectories and video observation reliability. Evaluation on challenging multi-person datasets suggests our fusion approach improves over motion-only and vision-only baselines in terms of both absolute and relative pose accuracy.

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/2608.29927 — 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 2026-10-17T09:28:48.090Z 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).