Metraipolis › archive › dc_f3e0bcb44ceb

Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes — arXiv:2611.03285

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03285
License (as archived)
CC0-1.0
Archived
2026-11-03T11:42:53.444Z
SHA-256 of the archived text
2d8e1fb3c813bf7ae862957b7d406c355d3fede24dbd80dc76f0e26d8af6c1a4
Stable URL of this page
https://metraipolis.com/documento/dc_f3e0bcb44ceb

How to cite

Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes — arXiv:2611.03285 — arXiv (en), https://arxiv.org/abs/2611.03285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3e0bcb44ceb (Metraipolis archive dc_f3e0bcb44ceb, sha256 2d8e1fb3c813bf7ae862957b7d406c355d3fede24dbd80dc76f0e26d8af6c1a4)
BibTeX
@misc{dcf3e0bcb44ceb,
  title = {Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes — arXiv:2611.03285},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03285},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3e0bcb44ceb; sha256 2d8e1fb3c813bf7ae862957b7d406c355d3fede24dbd80dc76f0e26d8af6c1a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Parametric human body models such as the Skinned Multi-Person Linear (SMPL) model provide compact representations of human shape and pose, but their reconstructions remain affected by both errors in estimated latent parameters and limitations in the decoder's expressive capacity. We propose a framework for refining these reconstructions by exploiting the geometric discrepancy between an initial decoded surface and a target mesh, without requiring vertex correspondences between them. The framework comprises three complementary approaches. Latent-VaRefine uses varifold-distance gradients to correct the estimated latent code while preserving the original parametric representation. Vertex-VaRefine processes multiscale varifold-gradient features with a DiffusionNet backbone to predict vertex displacements in a canonical pose, yielding an approximately pose-equivariant refinement pipeline. ElaOpt directly optimizes surface deformations under elastic regularization and normal-direction constraints.

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/2611.03285 — 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 2026-11-03T11:06:37.634Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).