Metraipolis › archive › dc_525946c19216

World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories — arXiv:2610.01742

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01742
License (as archived): CC0-1.0
Archived: 2026-10-06T19:16:52.828Z
SHA-256 of the archived text: 3edb248267c8430b55c9aa20d2f39ca28ea431c2984d2410d3d02f210493724a
Stable URL of this page: https://metraipolis.com/documento/dc_525946c19216

How to cite

World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories — arXiv:2610.01742 — arXiv (en), https://arxiv.org/abs/2610.01742 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_525946c19216 (Metraipolis archive dc_525946c19216, sha256 3edb248267c8430b55c9aa20d2f39ca28ea431c2984d2410d3d02f210493724a)

BibTeX

@misc{dc525946c19216,
  title = {World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories — arXiv:2610.01742},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01742},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_525946c19216; sha256 3edb248267c8430b55c9aa20d2f39ca28ea431c2984d2410d3d02f210493724a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01742. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Equipping artificial agents with spatial intelligence requires a comprehensive generative prior over the dynamic 3D world. We propose World Motion Models (WMMs) that capture "what was, is, and will be where across time" via sparse SE(3) pose trajectories. WMMs are built on the observation that elements of dynamic scenes can be well approximated by a set of rigid SE(3) trajectories, a minimal yet expressive primitive for 4D modeling. This representation unifies articulated objects, human bodies, hand-object interactions, piecewise-rigid scene dynamics, camera motion, and even robot states and actions into a single shared space. Given this representation, we cast the joint distribution of these entities as a flexible sequence modeling problem, utilizing flow-matching with per-token noise levels. Coupled with a context token mechanism for non-sequential conditioning, this formulation supports any-to-any marginal conditioning across an arbitrary number of entities and time steps. Tasks such as future prediction, motion infilling, model-predictive control, inverse kinematics, cross-embodiment retargeting, and policy learning all reduce to the application of different masks over the same network. Experiments on 6 diverse applications of 3D vision and robotics demonstrate the versatility and flexibility of WMMs with strong performance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01742 — 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 2026-10-06T17:37:36.954Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).