Metraipolis › archive › dc_488c484b2727

Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction — arXiv:2608.03379

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03379
License (as archived)
CC0-1.0
Archived
2026-10-31T12:58:24.897Z
SHA-256 of the archived text
9d8b5493e1977984a02db0525d26f420b4ce28d1a382e37d44ccee4a6a027b0f
Stable URL of this page
https://metraipolis.com/documento/dc_488c484b2727

How to cite

Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction — arXiv:2608.03379 — arXiv (en), https://arxiv.org/abs/2608.03379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_488c484b2727 (Metraipolis archive dc_488c484b2727, sha256 9d8b5493e1977984a02db0525d26f420b4ce28d1a382e37d44ccee4a6a027b0f)
BibTeX
@misc{dc488c484b2727,
  title = {Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction — arXiv:2608.03379},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03379},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_488c484b2727; sha256 9d8b5493e1977984a02db0525d26f420b4ce28d1a382e37d44ccee4a6a027b0f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D multi-person motion prediction requires modeling both individual kinematics and inter-person interactions. While Flow Matching is effective for multi-hypothesis generation to improve prediction accuracy, directly predicting skeletal sequences from pure noise often compromises structural consistency and introduces unreliable cross-agent interactions during early noise-dominated integration steps. To address this, we propose a Prior-Guided Residual Flow Matching framework. First, a Deterministic Coarse Prior (DCP) establishes a kinematic anchor, formulating the generative process as a conditional flow over motion residuals to simplify the generative objective and preserve structural stability. Second, a Dynamic Cross-Interaction (DCI) mechanism temporally synchronizes inter-agent message-passing with the integration progress, ensuring the extraction of reliable social contexts and improving multi-person motion fidelity. Finally, a decoupled joint-motion architecture with bidirectional fusion effectively preserves fine-grained kinematic coherence. Extensive experiments demonstrate that our approach achieves state-of-the-art prediction accuracy across multiple datasets. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03379 — 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 2026-10-31T12:45:33.246Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).