Metraipolis › archive › dc_3db60ab6df95
BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video — arXiv:2609.29850
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29850
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T06:44:47.030Z
- SHA-256 of the archived text
627ccf389ccca58e81b5007154de5584d757fd618693ee3a416e35ffb9fbcba9- Stable URL of this page
https://metraipolis.com/documento/dc_3db60ab6df95
How to cite
BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video — arXiv:2609.29850 — arXiv (en), https://arxiv.org/abs/2609.29850 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3db60ab6df95 (Metraipolis archive dc_3db60ab6df95, sha256 627ccf389ccca58e81b5007154de5584d757fd618693ee3a416e35ffb9fbcba9)
BibTeX
@misc{dc3db60ab6df95,
title = {BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video — arXiv:2609.29850},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29850},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3db60ab6df95; sha256 627ccf389ccca58e81b5007154de5584d757fd618693ee3a416e35ffb9fbcba9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29850. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning executable motions from human videos offers a scalable solution for humanoid robots to acquire demonstration motions. However, existing pipelines typically first construct an explicit human motion representation and then convert it into robot motions via motion retargeting. Although such methods can effectively leverage large volumes of existing human data for training, the substantial differences between humans and humanoid robots in locomotion mechanisms and joint degree-of-freedom configurations make motions generated by this human-representation-centric approach difficult to execute on robots. Furthermore, errors introduced during human motion estimation inevitably propagate to the retargeting stage and cannot be eliminated via joint optimization. We propose BeyondRetarget, an end-to-end framework that directly maps monocular RGB videos to robot motions. Discarding the explicit human representation, this framework learns robot-oriented implicit representations directly from visual observations, enabling the model to capture cross-morphology motion structures. To generate motions more suitable for robot execution, we further design a contact-aware motion optimization mechanism to improve temporal consistency and physical plausibility. Experiments show that BeyondRetarget significantly improves the accuracy and robustness of generated robot motions, while achieving higher execution success rates and lower latency in both simulation environments and real humanoid robots. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.29850 — 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 2026-10-08T06:09:29.937Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).