Using an image of a street in Germany, the team of researchers proved the algorithm efficiency by adapting visual styles copied from Vincent van Gogh, Edvard Munch and Pablo Picasso masterpieces.
The researchers have been able to produce these quite impressive images in less than an hour, and hope, by optimising their work, to deliver the images quicker in the future.
(Photo credit: Arxiv)
The original photograph depicting the Neckarfront in Tubingen, Germany, is shown in A. The painting that provided the style for the respective generated image is shown in the bottom left corner of each panel. B The Shipwreck of the Minotaur by J.M.W. Turner, 1805. C The Starry Night by Vincent van Gogh, 1889. D Der Schrei by Edvard Munch, 1893. E Femme nue assise by Pablo Picasso, 1910. F Composition VII by Wassily Kandinsky, 1913.
The technology behind the algorithm is called the convolutional neural network, which by creating a new image, copies the style of the artist.
The computer processes the work of the artist as a miror, trying to reproduce the human thoughts onto an input image.
(Photo credit: Arxiv)
An example of how the convolutional neural network works.
This science, part of the “deep learning” algorithms, is already used by Google for their image recognition and also for some of their apps.
“The system uses neural representations to separate and recombine content and style of arbitrary images, providing a neural algorithm for the creation of artistic images,” the researchers wrote in their paper, Arxiv.
Artists can be reassured, computers are only able to reproduce a predetermined pattern, meaning that creativity is still left to human's control.
Share
