Communication Dans Un Congrès Année : 2026

FALCON: Unfolded Variational Model for Blind Deconvolution and Segmentation in 3d Dental Imaging

Résumé

This paper proposes an unfolded variational network for joint 3D blind deconvolution and segmentation, derived from a Mumford-Shah (MS) estimation. The approach unrolls a Split Bregman optimization into a fixed number of learnable iterations, effectively combining model-driven regularization with data-driven parameter adaptation. When applied to Cone Beam Computed Tomography (CBCT) volumes, the approach restores fine anatomical details approaching micro-CT (µ-CT) quality while maintaining its interpretability through explicit variational terms. A subsequent clustering-based segmentation further refines the reconstructed structures, highlighting the potential of hybrid unfolding schemes to integrate physics-based priors and deep learning (DL) representations in 3D medical imaging.

Fichier principal
Vignette du fichier
1571220952 paper.pdf (467.2 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-05388103 , version 1 (28-11-2025)

Licence

Identifiants

  • HAL Id : hal-05388103 , version 1

Citer

Mario Amoros Rivera, Ouissem Smati, Jérôme Michetti, Manuel Curado, Jose Francisco Vicent, et al.. FALCON: Unfolded Variational Model for Blind Deconvolution and Segmentation in 3d Dental Imaging. IEEE International Symposium on Biomedical Imaging (ISBI) 2026, Apr 2026, London, United Kingdom. ⟨hal-05388103⟩
3168 Consultations
283 Téléchargements

Partager

  • More