Image reconstruction is frequently addressed by resorting to variational methods, which account for some prior knowledge about the solution. The success of these methods, however, heavily depends on the estimation of a set of hyperparameters. Deep learning architectures are, on the contrary, very generic and efficient, but they offer very limited control over their output. In this paper we present iRestNet, a neural network architecture which combines the benefits of both approaches. iRestNet is obtained by unfolding a proximal interior point algorithm. This enables enforcing hard constraints on the pixel range of the restored image thanks to a logarithmic barrier strategy, without requiring any parameter setting. Explicit expressions for the involved proximity operator, and its differential, are derived, which allows training iRestNet with gradient descent and backpropagation. Numerical experiments on image deblurring show that the proposed approach provides good image quality results compared to state-of-the-art variational and machine learning methods.

Learning image deblurring by unfolding a proximal interior point algorithm / Corbineau, M. -C.; Bertocchi, Carla; Chouzenoux, E.; Prato, M.; Pesquet, J. -C.. - 2019-:(2019), pp. 4664-4668. (Intervento presentato al convegno 26th IEEE International Conference on Image Processing, ICIP 2019 tenutosi a Taipei nel 22-25 settembre 2019) [10.1109/ICIP.2019.8803438].

Learning image deblurring by unfolding a proximal interior point algorithm

BERTOCCHI, CARLA;M. Prato;
2019

Abstract

Image reconstruction is frequently addressed by resorting to variational methods, which account for some prior knowledge about the solution. The success of these methods, however, heavily depends on the estimation of a set of hyperparameters. Deep learning architectures are, on the contrary, very generic and efficient, but they offer very limited control over their output. In this paper we present iRestNet, a neural network architecture which combines the benefits of both approaches. iRestNet is obtained by unfolding a proximal interior point algorithm. This enables enforcing hard constraints on the pixel range of the restored image thanks to a logarithmic barrier strategy, without requiring any parameter setting. Explicit expressions for the involved proximity operator, and its differential, are derived, which allows training iRestNet with gradient descent and backpropagation. Numerical experiments on image deblurring show that the proposed approach provides good image quality results compared to state-of-the-art variational and machine learning methods.
2019
26th IEEE International Conference on Image Processing, ICIP 2019
Taipei
22-25 settembre 2019
2019-
4664
4668
Corbineau, M. -C.; Bertocchi, Carla; Chouzenoux, E.; Prato, M.; Pesquet, J. -C.
Learning image deblurring by unfolding a proximal interior point algorithm / Corbineau, M. -C.; Bertocchi, Carla; Chouzenoux, E.; Prato, M.; Pesquet, J. -C.. - 2019-:(2019), pp. 4664-4668. (Intervento presentato al convegno 26th IEEE International Conference on Image Processing, ICIP 2019 tenutosi a Taipei nel 22-25 settembre 2019) [10.1109/ICIP.2019.8803438].
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1176859
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 6
social impact