Metraipolis › archive › dc_3f614d29ede5

World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation — arXiv:2610.27725

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27725
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:02.009Z
SHA-256 of the archived text
a73d3185f0409d296e6e2aefc9ea92c9cfb5029422896d9ae203eb070ab76b3f
Stable URL of this page
https://metraipolis.com/documento/dc_3f614d29ede5

How to cite

World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation — arXiv:2610.27725 — arXiv (en), https://arxiv.org/abs/2610.27725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f614d29ede5 (Metraipolis archive dc_3f614d29ede5, sha256 a73d3185f0409d296e6e2aefc9ea92c9cfb5029422896d9ae203eb070ab76b3f)
BibTeX
@misc{dc3f614d29ede5,
  title = {World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation — arXiv:2610.27725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f614d29ede5; sha256 a73d3185f0409d296e6e2aefc9ea92c9cfb5029422896d9ae203eb070ab76b3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon human-object-scene interaction (HOSI) is central to embodied AI, animation, and game development. Existing human-object interaction (HOI) and human-scene interaction (HSI) models excel in their respective domains, but none alone covers tasks requiring multiple interaction skills. Training unified HOSI models is hindered by scarce and costly data. We introduce World2HOSI, a multi-expert orchestration harness that generates continuous HOSI data from 3D Gaussian Splatting (3DGS) scenes and natural language instructions. Our key insight is that long-horizon HOSI hinges not on a stronger single model but on orchestration. Given a shared, structured scene state and an orchestration harness grounded in it, existing experts can jointly accomplish tasks beyond the reach of any of them alone. World2HOSI realizes this insight as a closed loop around a persistent scene state built from decoupled background and object assets. A harness plans action stages over this state, invokes experts via their native conditioning interfaces, and writes each action's effects back, so that every invocation is grounded in the evolving world. To reduce physical artifacts, bounded residual optimization and contact-driven physics simulation further ensure the physical plausibility of human motion and object manipulation, respectively, while preserving interaction intent. Experiments and a perceptual user study show that World2HOSI achieves the best task completion and interaction quality on the evaluated HOSI tasks, while generating more diverse data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27725 — 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 2026-10-21T07:05:43.594Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).