Metraipolis › archive › dc_eb3ced280d83

DEAL-Grasp: Decoupled Alignment Representation for Geometry-Aware Dexterous Grasp Generation — arXiv:2609.28131

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.28131
License (as archived): CC0-1.0
Archived: 2026-10-08T12:53:45.931Z
SHA-256 of the archived text: 4e2da173327b26697f85d7873e1f83b1c0e47540d284a3f5acb62f997772137e
Stable URL of this page: https://metraipolis.com/documento/dc_eb3ced280d83

How to cite

DEAL-Grasp: Decoupled Alignment Representation for Geometry-Aware Dexterous Grasp Generation — arXiv:2609.28131 — arXiv (en), https://arxiv.org/abs/2609.28131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb3ced280d83 (Metraipolis archive dc_eb3ced280d83, sha256 4e2da173327b26697f85d7873e1f83b1c0e47540d284a3f5acb62f997772137e)

BibTeX

@misc{dceb3ced280d83,
  title = {DEAL-Grasp: Decoupled Alignment Representation for Geometry-Aware Dexterous Grasp Generation — arXiv:2609.28131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb3ced280d83; sha256 4e2da173327b26697f85d7873e1f83b1c0e47540d284a3f5acb62f997772137e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthesizing realistic articulated hand-object interactions is a fundamental problem in virtual reality, embodied intelligence, and digital human applications. Existing methods for dexterous grasp synthesis typically regress or denoise poses in a joint space that couples global rigid motion with local articulation, which often yields unstable samples and physically implausible contacts. We introduce DEAL-Grasp, built upon the Decoupled Alignment (DEAL) representation, which reformulates grasp synthesis as alignment-space generation: the interaction state comprises task-space geometric anchors and articulation parameters, from which the rigid transform is recovered via closed-form Procrustes alignment while preserving local articulation. On this mixed state, we model grasp generation using heterogeneous-state flow matching with component-wise vector fields, incorporating time-adaptive physical regularization during training. At inference, grasps are synthesized solely by integrating the learned vector field, without test-time optimization or auxiliary physical guidance. Across MultiDex and zero-shot RealDex benchmarks, DEAL-Grasp attains high force-perturbation success rates alongside minimal penetration and high diversity of generated grasps, while substantially reducing native inference latency compared to optimization-heavy baselines. The project page is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.28131 — 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 2026-10-08T12:21:19.498Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).