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. (c) 2017 SPIE and IS&T |
Year | DOI | Venue |
---|---|---|
2018 | 10.1117/1.JEI.27.1.011004 | JOURNAL OF ELECTRONIC IMAGING |
Keywords | Field | DocType |
photographic filters,convolutional neural networks,image restoration | Computer vision,Pattern recognition,Polynomial,Computer science,Convolutional neural network,Artificial intelligence,Image restoration | Journal |
Volume | Issue | ISSN |
27 | 1 | 1017-9909 |
Citations | PageRank | References |
1 | 0.36 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Bianco | 1 | 226 | 24.48 |
Claudio Cusano | 2 | 373 | 23.05 |
Flavio Piccoli | 3 | 16 | 2.09 |
Raimondo Schettini | 4 | 1476 | 154.06 |