Metraipolis › archive › dc_1dd82048bb22

DisFace3DNet: Explainable Facial Attractiveness Prediction via 3D Component Disentanglement — arXiv:2610.11656

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11656
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:37.561Z
SHA-256 of the archived text
6456d7efa6eac3ac8ff77965738205132a2f01c35f558ddd1d11e6640743f344
Stable URL of this page
https://metraipolis.com/documento/dc_1dd82048bb22

How to cite

DisFace3DNet: Explainable Facial Attractiveness Prediction via 3D Component Disentanglement — arXiv:2610.11656 — arXiv (en), https://arxiv.org/abs/2610.11656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1dd82048bb22 (Metraipolis archive dc_1dd82048bb22, sha256 6456d7efa6eac3ac8ff77965738205132a2f01c35f558ddd1d11e6640743f344)
BibTeX
@misc{dc1dd82048bb22,
  title = {DisFace3DNet: Explainable Facial Attractiveness Prediction via 3D Component Disentanglement — arXiv:2610.11656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1dd82048bb22; sha256 6456d7efa6eac3ac8ff77965738205132a2f01c35f558ddd1d11e6640743f344},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Facial attractiveness prediction usually assigns one overall rating, leaving the roles of shape, appearance, and viewing conditions implicit. We propose DisFace3DNet, which uses 3D component disentanglement to learn seven component reference scores from overall ratings with auxiliary weak semantic supervision, without human-labeled component targets. Designated 3D representations and image cues feed jointly learned routes for identity, skin, hair, light, background, expression, and pose. A constrained fit then combines five static and two signed dynamic scores into the overall rating, exposing each component's numerical contribution and supporting component-specific comparisons across images. On SCUT-FBP5500, DisFace3DNet achieves a Pearson correlation of $0.8904\pm0.0063$ (mean $\pm$ standard deviation across five folds) with average human ratings; its component terms reconstruct every held-out prediction to numerical precision. Skin, hair, and facial shape account for the largest component-wise prediction variation. Human evaluation supports the score directions for facial shape, skin, and hair; expression agreement is weaker. DisFace3DNet thus connects overall prediction to quantitative analysis of the facial and contextual cues entering each estimate.

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/2610.11656 — 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 2026-10-09T05:55:07.486Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).