Metraipolis › archive › dc_fb3bb8a2be0d

DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction — arXiv:2609.36454

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36454
License (as archived): CC0-1.0
Archived: 2026-10-07T18:38:11.802Z
SHA-256 of the archived text: 87c709fec4ba85561909ce62dde807bc2cba5363d575efa610aedb150524f31d
Stable URL of this page: https://metraipolis.com/documento/dc_fb3bb8a2be0d

How to cite

DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction — arXiv:2609.36454 — arXiv (en), https://arxiv.org/abs/2609.36454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb3bb8a2be0d (Metraipolis archive dc_fb3bb8a2be0d, sha256 87c709fec4ba85561909ce62dde807bc2cba5363d575efa610aedb150524f31d)

BibTeX

@misc{dcfb3bb8a2be0d,
  title = {DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction — arXiv:2609.36454},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb3bb8a2be0d; sha256 87c709fec4ba85561909ce62dde807bc2cba5363d575efa610aedb150524f31d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study hand-object interaction (HOI) reconstruction from monocular RGB videos, where partial observations can produce visually plausible yet mechanically inconsistent trajectories. Existing methods mainly enforce visual and geometric agreement, leaving the underlying interaction dynamics insufficiently constrained. We propose DynamicHOI, a physics-aware HOI reconstruction framework combining geometry-grounded diffusion refinement with coupled hand-object dynamics. Geometry spatially grounds visual evidence for trajectory refinement, while articulated inverse dynamics and Newton-Euler dynamics derive hand generalized forces and object wrenches for dynamics-level supervision. We further couple hand and object dynamics through contact-force transfer and recover active hand actuation as an interaction-level physical quantity. We formulate its empirical magnitude distribution into a probabilistic prior that penalizes unlikely actuation and suppresses mechanically implausible reconstructed motion. Experiments on three HOI datasets show consistent improvements in both hand and object reconstruction. The reconstructed trajectories further benefit downstream applications including hand world-model generation and robotic manipulation learning, demonstrating the value of physics-aware HOI modeling beyond reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.36454 — 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 2026-10-07T18:04:24.706Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).