A Neural Network Looks at Leonardo's(?) Salvator Mundi
This work addresses art authentication challenges for historians and art experts, but it is incremental as it applies existing CNN methods to a new domain without major methodological innovations.
The authors tackled the problem of authenticating Leonardo da Vinci's paintings, specifically Salvator Mundi, by using convolutional neural networks trained on his works and those of other artists to identify forgeries and resolve attribution issues, though the limited number of his extant paintings required additional corroborative analysis.
We use convolutional neural networks (CNNs) to analyze authorship questions surrounding the works of Leonardo da Vinci -- in particular, Salvator Mundi, the world's most expensive painting and among the most controversial. Trained on the works of an artist under study and visually comparable works of other artists, our system can identify likely forgeries and shed light on attribution controversies. Leonardo's few extant paintings test the limits of our system and require corroborative techniques of testing and analysis.