Metraipolis › archive › dc_208f9980fb2f

VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation — arXiv:2610.10197

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10197
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:55.762Z
SHA-256 of the archived text
1fb9727e8a7451e16f1bb5fddc1595468df444b515eafa6cb47a6878df265594
Stable URL of this page
https://metraipolis.com/documento/dc_208f9980fb2f

How to cite

VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation — arXiv:2610.10197 — arXiv (en), https://arxiv.org/abs/2610.10197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_208f9980fb2f (Metraipolis archive dc_208f9980fb2f, sha256 1fb9727e8a7451e16f1bb5fddc1595468df444b515eafa6cb47a6878df265594)
BibTeX
@misc{dc208f9980fb2f,
  title = {VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation — arXiv:2610.10197},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10197},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_208f9980fb2f; sha256 1fb9727e8a7451e16f1bb5fddc1595468df444b515eafa6cb47a6878df265594},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate contact modeling is fundamental to understanding hand-object interaction, yet existing contact representations are typically restricted to object surfaces and rely on hand-crafted rules to recover contact details, leading to severe penetrations and implausible results. To better exploit the rich detail in motion-capture data, we introduce Volumetric Contact (VolCo), a representation that expands surface points to a set of 3D volumetric grids. VolCo encodes 3D contact that allows precise hand part recovery, and is organized in an inherent hierarchy: local contact details within each volume and global hand geometry across all volumes. Our framework, VolCoDiff, employs two modules to capture local and global features following this hierarchy. For local contact details, we use a 3D variational autoencoder to model the possible hand configurations conditioned on the local object signed distance field (SDF). For global hand geometry, we design a prior-guided diffusion model that learns the distribution of compressed latent features aggregated from the volumetric grids. We evaluate our method on two benchmark datasets and demonstrate state-of-the-art performance in penetration and stability, indicating the capability to generate tight grasps with much less severe penetrations. Our code 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/2610.10197 — 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 2026-10-08T12:18:15.463Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).