Deep learning methods have state-of-The-Art performances in many image restoration tasks. Their effectiveness is mostly related to the size of the dataset used for the training. Deep image prior (DIP) is an energy-function framework which eliminates the dependency on the training set, by considering the structure of a neural network as an handcrafted prior offering high impedance to noise and low impedance to signal. In this paper, we analyze and compare the use of different optimization schemes inside the DIP framework for the denoising task.

On the First-Order Optimization Methods in Deep Image Prior / Cascarano, P.; Franchini, G.; Porta, F.; Sebastiani, A.. - In: JOURNAL OF VERIFICATION, VALIDATION AND UNCERTAINTY QUANTIFICATION. - ISSN 2377-2158. - 7:4(2022), pp. 041002-041002. [10.1115/1.4056470]

On the First-Order Optimization Methods in Deep Image Prior

Franchini G.;Porta F.;
2022

Abstract

Deep learning methods have state-of-The-Art performances in many image restoration tasks. Their effectiveness is mostly related to the size of the dataset used for the training. Deep image prior (DIP) is an energy-function framework which eliminates the dependency on the training set, by considering the structure of a neural network as an handcrafted prior offering high impedance to noise and low impedance to signal. In this paper, we analyze and compare the use of different optimization schemes inside the DIP framework for the denoising task.
2022
7
4
041002
041002
On the First-Order Optimization Methods in Deep Image Prior / Cascarano, P.; Franchini, G.; Porta, F.; Sebastiani, A.. - In: JOURNAL OF VERIFICATION, VALIDATION AND UNCERTAINTY QUANTIFICATION. - ISSN 2377-2158. - 7:4(2022), pp. 041002-041002. [10.1115/1.4056470]
Cascarano, P.; Franchini, G.; Porta, F.; Sebastiani, A.
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/11380/1306507
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact