Metraipolis › archive › dc_ac68aaa73ac2

OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching — arXiv:2610.19857

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19857
License (as archived): CC0-1.0
Archived: 2026-10-15T21:56:42.798Z
SHA-256 of the archived text: 57e6cf15729267de1c8067f3f185e662149bbaddab288fb887e2c5fd92a61934
Stable URL of this page: https://metraipolis.com/documento/dc_ac68aaa73ac2

How to cite

OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching — arXiv:2610.19857 — arXiv (en), https://arxiv.org/abs/2610.19857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac68aaa73ac2 (Metraipolis archive dc_ac68aaa73ac2, sha256 57e6cf15729267de1c8067f3f185e662149bbaddab288fb887e2c5fd92a61934)

BibTeX

@misc{dcac68aaa73ac2,
  title = {OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching — arXiv:2610.19857},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19857},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac68aaa73ac2; sha256 57e6cf15729267de1c8067f3f185e662149bbaddab288fb887e2c5fd92a61934},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking signals. Existing approaches are restricted to fixed sensor configurations and, when built on diffusion models, are computationally prohibitive for real-time deployment. We propose OmniPoser, a universal framework that recovers full-body SMPL motion from a flexible combination of heterogeneous inputs, such as 3D keypoints, sparse IMU rotations, head-mounted 6-DoF poses, or any subset thereof, within a single model. OmniPoser introduces a cross-modal masking mechanism paired with a Masked Conditioning Encoder, enabling one architecture to incorporate diverse sensor configurations through a masked design. A decoupled dual-stream generative backbone generates complete motion via Conditional Flow Matching, requiring only a single ODE integration step at inference. Across three settings and seven benchmarks, including in-the-wild Nymeria and Ego-Exo4D datasets, OmniPoser performs on par with state-of-the-art methods while running at over 700 FPS. The project page is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19857 — 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 2026-10-15T21:38:29.507Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).