We present a method for the automatic restoration of images subjected to the application of photographic filters, such as those made popular by photo-sharing services. The method uses a convolutional neural network (CNN) for the prediction of the coefficients of local polynomial transformations that are applied to the input image. The experiments we conducted on a subset of the Places-205 dataset show that the quality of the restoration performed by our method is clearly superior to that of traditional color balancing and restoration procedures, and to that of recent CNN architectures for image-to-image translation.

Schettini, R., Piccoli, F., Cusano, C., Bianco, S. (2018). Artistic photo filter removal using convolutional neural networks. JOURNAL OF ELECTRONIC IMAGING, 27(1), 1-14 [10.1117/1.JEI.27.1.011004].

Artistic photo filter removal using convolutional neural networks

Schettini, R;PICCOLI, FLAVIO;Cusano, C;Bianco, S.
2018

Abstract

We present a method for the automatic restoration of images subjected to the application of photographic filters, such as those made popular by photo-sharing services. The method uses a convolutional neural network (CNN) for the prediction of the coefficients of local polynomial transformations that are applied to the input image. The experiments we conducted on a subset of the Places-205 dataset show that the quality of the restoration performed by our method is clearly superior to that of traditional color balancing and restoration procedures, and to that of recent CNN architectures for image-to-image translation.
Articolo in rivista - Articolo scientifico
convolutional neural networks; image restoration; Photographic filters;
photographic filters; convolutional neural networks; image restoration
English
2018
27
1
1
14
011004
none
Schettini, R., Piccoli, F., Cusano, C., Bianco, S. (2018). Artistic photo filter removal using convolutional neural networks. JOURNAL OF ELECTRONIC IMAGING, 27(1), 1-14 [10.1117/1.JEI.27.1.011004].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/10281/179800
Citazioni
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 3
Social impact