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.
Pubblicazioni consigliate
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
