Metraipolis › archive › dc_d7dc0f99e422

Streaming Multi-Track Timeline Control for 3D Human Motion Generation — arXiv:2610.03873

Source
arXiv
Original
https://arxiv.org/abs/2610.03873
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:53.419Z
SHA-256 of the archived text
8d5496b260ef974b5c6cb01bf2fc23de592e7bd0fce73b525acac6b3e0a49c6a
Stable URL of this page
https://metraipolis.com/documento/dc_d7dc0f99e422

How to cite

Streaming Multi-Track Timeline Control for 3D Human Motion Generation — arXiv:2610.03873 — arXiv, https://arxiv.org/abs/2610.03873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7dc0f99e422 (Metraipolis archive dc_d7dc0f99e422, sha256 8d5496b260ef974b5c6cb01bf2fc23de592e7bd0fce73b525acac6b3e0a49c6a)
BibTeX
@misc{dcd7dc0f99e422,
  title = {Streaming Multi-Track Timeline Control for 3D Human Motion Generation — arXiv:2610.03873},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03873},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7dc0f99e422; sha256 8d5496b260ef974b5c6cb01bf2fc23de592e7bd0fce73b525acac6b3e0a49c6a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applications require responding to new instructions while continuing ongoing actions, such as answering a phone while walking. Existing approaches address streaming generation or simultaneous composition without explicitly combining streaming instruction arrival with independently timed, overlapping actions. We introduce streaming multi-track timeline control and propose TimelineControl to incorporate new instructions alongside ongoing actions. Interval-aware conditioning preserves instruction timing, while causal part-structured representations and part-aware denoising coordinate concurrent actions across body regions. We also construct TimelineMotion, a dataset with overlapping instruction intervals and body-part annotations. Experiments on TimelineMotion and MTT demonstrate improved semantic alignment and temporal adherence over evaluated streaming baselines, including models retrained on the same data. Ablations and human evaluations validate our design, complemented by spatial conditioning and humanoid execution demonstrations. Our code, data and models will become publicly available.

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); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03873 — 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 2026-10-06T05:24:05.759Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).