Metraipolis › archive › dc_0c04880ed048

Unified Motion Retargeting for Humanoids with Learned Point Cloud Correspondence — arXiv:2609.02134

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02134
License (as archived)
CC0-1.0
Archived
2026-10-17T05:51:12.984Z
SHA-256 of the archived text
1723a4047d02fd535f9d3ff5e8aa639e461d76b4c6429231a5e5a26b604a9c39
Stable URL of this page
https://metraipolis.com/documento/dc_0c04880ed048

How to cite

Unified Motion Retargeting for Humanoids with Learned Point Cloud Correspondence — arXiv:2609.02134 — arXiv (en), https://arxiv.org/abs/2609.02134 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c04880ed048 (Metraipolis archive dc_0c04880ed048, sha256 1723a4047d02fd535f9d3ff5e8aa639e461d76b4c6429231a5e5a26b604a9c39)
BibTeX
@misc{dc0c04880ed048,
  title = {Unified Motion Retargeting for Humanoids with Learned Point Cloud Correspondence — arXiv:2609.02134},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02134},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c04880ed048; sha256 1723a4047d02fd535f9d3ff5e8aa639e461d76b4c6429231a5e5a26b604a9c39},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02134. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid learning increasingly relies on transforming vast and diverse human motion data into high-quality robot reference trajectories. However, retargeting human motion to humanoid robots is challenging due to substantial differences in morphology, degrees of freedom, joint ranges, and kinematic constraints between humans and robots. Existing retargeting methods typically address these differences by defining human-robot correspondence through hand-crafted sparse keypoints or body-part pairs. As a result, retargeting quality depends heavily on manual semantic design, limiting scalability across motion sources and robot morphologies and providing only sparse guidance for reproducing detailed poses and interactions. In this paper, we present Unified Motion Retargeting (UMR), a framework that learns dense point cloud correspondence without requiring manually designed human-robot mappings. By treating exterior point clouds as a unified interface between human motion and humanoid robots, UMR decouples retargeting from source-specific skeletal semantics and robot-specific topology. The learned dense correspondence provides fine-grained geometric anchors for constrained point cloud matching optimization, enabling surface-level pose alignment and direct transfer of interaction contacts. Experiments demonstrate that UMR unifies retargeting across heterogeneous motion sources, robot embodiments, and downstream scenarios ranging from locomotion to interaction, while achieving higher motion fidelity and plausibility than state-of-the-art methods. UMR therefore provides a scalable foundation for transforming large-scale human motion references into robot-ready training data.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.02134 — 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 2026-10-17T05:39:02.674Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).