In the last decades, unsupervised deep learning based methods have caught researchers' attention, since in many real applications, such as medical imaging, collecting a large amount of training examples is not always feasible. Moreover, the construction of a good training set is time consuming and hard because the selected data have to be enough representative for the task. In this paper, we focus on the Deep Image Prior (DIP) framework and we propose to combine it with a space-variant Total Variation regularizer with an automatic estimation of the local regularization parameters. Differently from other existing approaches, we solve the arising minimization problem via the flexible Alternating Direction Method of Multipliers (ADMM). Furthermore, we provide a specific implementation also for the standard isotropic Total Variation. The promising performances of the proposed approach, in terms of PSNR and SSIM values, are addressed through several experiments on simulated as well as real natural and medical corrupted images.

Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM / Cascarano, Pasquale; Sebastiani, Andrea; Comes, Maria Colomba; Franchini, Giorgia; Porta, Federica. - ELETTRONICO. - (2021), pp. 39-46. (Intervento presentato al convegno 21st International Conference on Computational Science and Its Applications, ICCSA 2021 tenutosi a Cagliari nel 13-16 Settembre) [10.1109/iccsa54496.2021.00016].

Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM

Cascarano, Pasquale;Sebastiani, Andrea;Porta, Federica
2021

Abstract

In the last decades, unsupervised deep learning based methods have caught researchers' attention, since in many real applications, such as medical imaging, collecting a large amount of training examples is not always feasible. Moreover, the construction of a good training set is time consuming and hard because the selected data have to be enough representative for the task. In this paper, we focus on the Deep Image Prior (DIP) framework and we propose to combine it with a space-variant Total Variation regularizer with an automatic estimation of the local regularization parameters. Differently from other existing approaches, we solve the arising minimization problem via the flexible Alternating Direction Method of Multipliers (ADMM). Furthermore, we provide a specific implementation also for the standard isotropic Total Variation. The promising performances of the proposed approach, in terms of PSNR and SSIM values, are addressed through several experiments on simulated as well as real natural and medical corrupted images.
2021
2021 21st International Conference on Computational Science and Its Applications (ICCSA)
39
46
Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM / Cascarano, Pasquale; Sebastiani, Andrea; Comes, Maria Colomba; Franchini, Giorgia; Porta, Federica. - ELETTRONICO. - (2021), pp. 39-46. (Intervento presentato al convegno 21st International Conference on Computational Science and Its Applications, ICCSA 2021 tenutosi a Cagliari nel 13-16 Settembre) [10.1109/iccsa54496.2021.00016].
Cascarano, Pasquale; Sebastiani, Andrea; Comes, Maria Colomba; Franchini, Giorgia; Porta, Federica
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/964577
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 21
social impact