Metraipolis › archive › dc_83e2fda7d5d9

Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity — arXiv:2610.09032

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09032
License (as archived)
CC0-1.0
Archived
2026-10-08T12:46:52.393Z
SHA-256 of the archived text
aee55f889014ddf2b48b11cb337af6797032387d042fdd5a97252de8607ca688
Stable URL of this page
https://metraipolis.com/documento/dc_83e2fda7d5d9

How to cite

Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity — arXiv:2610.09032 — arXiv (en), https://arxiv.org/abs/2610.09032 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83e2fda7d5d9 (Metraipolis archive dc_83e2fda7d5d9, sha256 aee55f889014ddf2b48b11cb337af6797032387d042fdd5a97252de8607ca688)
BibTeX
@misc{dc83e2fda7d5d9,
  title = {Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity — arXiv:2610.09032},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09032},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83e2fda7d5d9; sha256 aee55f889014ddf2b48b11cb337af6797032387d042fdd5a97252de8607ca688},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09032. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Perceiving structured shapes, such as human faces, from pixels is an inherently ambiguous task in real-world conditions. Yet, shape inference is largely posed as a deterministic regression task predicting fixed spatial coordinates. We find that deterministic regression is brittle when visual evidence is ambiguous or incomplete; under severe occlusions deterministic models exhibit structural collapse, predicting incoherent shapes or reverting to generic averages. To address this, we introduce Shape-Bayes, a probabilistic framework that couples uncertainty-aware visual perception with Bayesian shape reasoning. Rather than forcing point estimates, Shape-Bayes dynamically weights visual evidence against geometric priors to infer a structurally valid shape posterior. Demonstrated on human face shape regression, a rigorous testbed featuring complex non-rigid deformations and strict anatomical constraints, Shape-Bayes comprises: (1) a base model predicting noisy landmarks alongside distilled aleatoric uncertainties; (2) a lightweight Transformer encoding these observations into an adaptive prior over a PCA shape manifold; and (3) a differentiable Bayesian solver computing closed-form posteriors by balancing the noisy predictions against this prior. By guaranteeing complete structural integrity, Shape-Bayes achieves an absolute improvement of up to ~34% IDR over state-of-the-art deterministic models. Simultaneously, it yields highly calibrated uncertainty bounds and reduces relative error by up to 12.5%, establishing a new state-of-the-art for robust 2D face shape regression under severe occlusion. The project page is 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/2610.09032 — 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 2026-10-08T12:18:15.286Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).