Metraipolis › archive › dc_7885ce293bbd

Multi-Person Human Motion Forecasting in Complex Scenes — arXiv:2608.27039

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.27039
License (as archived): CC0-1.0
Archived: 2026-10-17T14:30:25.285Z
SHA-256 of the archived text: 1678986f3d0ef1563fb9cc45427069c99531b866532abe69d08cedac3b5a70f7
Stable URL of this page: https://metraipolis.com/documento/dc_7885ce293bbd

How to cite

Multi-Person Human Motion Forecasting in Complex Scenes — arXiv:2608.27039 — arXiv (en), https://arxiv.org/abs/2608.27039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7885ce293bbd (Metraipolis archive dc_7885ce293bbd, sha256 1678986f3d0ef1563fb9cc45427069c99531b866532abe69d08cedac3b5a70f7)

BibTeX

@misc{dc7885ce293bbd,
  title = {Multi-Person Human Motion Forecasting in Complex Scenes — arXiv:2608.27039},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7885ce293bbd; sha256 1678986f3d0ef1563fb9cc45427069c99531b866532abe69d08cedac3b5a70f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurately forecasting the movement of people in complex scenes requires reasoning over the past and present state of the entire environment. In this context, effectively incorporating object information and social interactions into a unified framework remains particularly challenging. To address this, we propose Object-Conditioned Social Diffusion (OCSD), a conditional diffusion model that integrates motion history, multi-person interactions, and object cues into a single framework. OCSD uses an object-conditioning mechanism that modulates denoising at every timestep, enabling fine-grained human-object reasoning, and a social encoder that models the interactions between all humans in the scene. As a result, our model naturally handles varying group sizes, complex social interactions, and supports sampling multiple plausible futures. Extensive experiments show that OCSD achieves state-of-the-art results on the Humans in Kitchens (HiK) and HOI-M3 benchmarks. It reduces the two-second path error by 121.5 mm (31.3%) on HiK and 130.5 mm (33.2%) on HOI-M3 compared to prior work, and produces more realistic long-term forecasts.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27039 — 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 2026-10-17T13:16:53.681Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).