Metraipolis › archive › dc_9cc3d4aaa349
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark — arXiv:2608.13555
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13555
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:18:38.502Z
- SHA-256 of the archived text
e5652d5c1661b39a01f5ba7e3b314319bf3aec919e8d2737dffc2df80fb62f21- Stable URL of this page
https://metraipolis.com/documento/dc_9cc3d4aaa349
How to cite
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark — arXiv:2608.13555 — arXiv (en), https://arxiv.org/abs/2608.13555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9cc3d4aaa349 (Metraipolis archive dc_9cc3d4aaa349, sha256 e5652d5c1661b39a01f5ba7e3b314319bf3aec919e8d2737dffc2df80fb62f21)
BibTeX
@misc{dc9cc3d4aaa349,
title = {HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark — arXiv:2608.13555},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13555},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9cc3d4aaa349; sha256 e5652d5c1661b39a01f5ba7e3b314319bf3aec919e8d2737dffc2df80fb62f21},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect contacts such as foot skating and mistimed touch-downs. Meanwhile, widely used test suites are small and lack the diversity needed to stress contact-rich, long-horizon behaviors. We introduce HumanTracker to make humanoid tracking evaluation both perceptually aligned and scalable. The HumanTracker benchmark contains approximately 153 hours of optical motion trajectories from multiple professional performers, organized into four motion families with text labels for fine-grained diagnosis. We further propose HumanScore, a preference-aligned metric trained on 12K motion pairs containing 24K motions. Across representative state-of-the-art trackers, HumanScore better predicts human preferences and reveals contact and stability failures that kinematic metrics often miss. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.13555 — 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 2026-10-19T04:13:06.786Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).