Researchers in Germany have developed an algorithm capable of recreating the style of famous artists, including Van Gogh and Picasso, in under an hour. “The key finding … is that the representations of content [the foundation image] and style [of specific artworks] in the convolutional neural network are separable,” says lead author Leon Gatys. “That is, we can manipulate both representations independently to produce new, perceptually meaningful images.”
Read more at The Guardian