Back to articles
Articles
Volume: 33 | Article ID: art00006
Image
Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars
  DOI :  10.2352/ISSN.2470-1173.2021.14.CVAA-042  Published OnlineJanuary 2021
Abstract

We describe the application of convolutional neural network style transfer to the problem of improved visualization of underdrawings and ghost-paintings in fine art oil paintings. Such underdrawings and hidden paintings are typically revealed by x-ray or infrared techniques which yield images that are grayscale, and thus devoid of color and full style information. Past methods for inferring color in underdrawings have been based on physical x-ray uorescence spectral imaging of pigments in ghost-paintings and are thus expensive, time consuming, and require equipment not available in most conservation studios. Our algorithmic methods do not need such expensive physical imaging devices. Our proof-ofconcept system, applied to works by Pablo Picasso and Leonardo, reveal colors and designs that respect the natural segmentation in the ghost-painting. We believe the computed images provide insight into the artist and associated oeuvre not available by other means. Our results strongly suggest that future applications based on larger corpora of paintings for training will display color schemes and designs that even more closely resemble works of the artist. For these reasons refinements to our methods should find wide use in art conservation, connoisseurship, and art analysis.

Subject Areas :
Views 28
Downloads 7
 articleview.views 28
 articleview.downloads 7
  Cite this article 

Anthony Bourached, George H. Cann, Ryan-Rhys Griffths, David G. Stork, "Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholarsin Proc. IS&T Int’l. Symp. on Electronic Imaging: Computer Vision and Image Analysis of Art,  2021,  pp 42-1 - 42-10,  https://doi.org/10.2352/ISSN.2470-1173.2021.14.CVAA-042

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA