• Subscribe

Algorithms for Art

Speed read
  • Automation is shaking up the job market
  • German researchers develop style transfer art algorithm
  • Fine artists’ jobs are relatively safe — for the time being

In August, we ran a story about employment in the age of automation. We mentioned which jobs are most at risk of being automated, and pointed to an online tool that will help you determine the relative security of your occupation.

Jobs in the creative fields are in the low-risk category — but artists beware! Algorithms are learning to create from masters like Van Gogh, Monet, and Kandinsky.

Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge from the University of Tübingen in Germany have created an algorithm that creates new works of art by transferring the style of one image to another.

The system uses a Deep Neural Network with the ability to separate the style of an image from its content. TThe researchers believe that, as humans, our appreciation of the new art form derives from the ability to differentiate between these two elements.

Gatys’s group used their algorithm to create a web app called Deep Art. To make art with the app, simply upload an image, choose a style, and wait. The app sends you an email when the image is ready for viewing.

Using the app, Australian artist and writer Chris Rodley create a viral social media image of a book of dinosaurs crossed with a book of flowers.

Rodley is also known for his use of the Deep Art app to merge various photos of Donald Trump with pictures of Jim Henson’s Muppets.

<strong>Cross purposes.</strong> What do you get when you cross Jim Henson's Muppets and the Trump family? The results are unsettling. Courtesy Chris Rodley.

Google’s Deep Dream neural imaging network functions similarly. An app called Dreamscope uses this technology to let users upload photos and run them through Deep Dream’s many patterns. 

Another Google product, AutoDraw, is a web-based tool that pairs machine learning with drawings created by actual artists. It makes drawing quick and easy for novices. Google researchers have also developed machine learning that can write poetry that some have called ‘hauntingly beautiful.’ (Pro tip: it is better when read backwards.)

The Will Robots Take My Job? tool says that fine artists have only a 4.2 percent chance of being replaced by machines.

With apps like Deep Art, will the outlook be that positive in ten years?

See how the neural style transfer algorithm was put to use in Kristen Stewart's directorial debut Come Swim. 

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2018 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.


We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.