23 December 2017 Artistic photo filter removal using convolutional neural networks
Author Affiliations +
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.
© 2017 SPIE and IS&T
Simone Bianco, Claudio Cusano, Flavio Piccoli, Raimondo Schettini, "Artistic photo filter removal using convolutional neural networks," Journal of Electronic Imaging 27(1), 011004 (23 December 2017). https://doi.org/10.1117/1.JEI.27.1.011004 . Submission: Received: 1 August 2017; Accepted: 22 November 2017
Received: 1 August 2017; Accepted: 22 November 2017; Published: 23 December 2017
JOURNAL ARTICLE
14 PAGES


SHARE
RELATED CONTENT


Back to Top