Neural algorithm makes photos emulate famous paintings

Back in 2003 we blew a lot of minds by showing Photoshop’s Match Color feature sucking up the color palette of one photo or painting, then depositing it onto another. This kind of thing kept getting love as it evolved (see 2010 demo), eventually matching lighting among images. As far as I know no one has ended up using such functionality in practice (and yes, Match Color is still sitting in Photoshop on your hard drive right now), but it’s still cool.

Now the tech has taken another leap forward. Per PetaPixel,

In a newly published research paper titled “A Neural Algorithm of Artistic Style,” scientists at the University of Tubingen in Germany describe how their deep neural network can create new artistic images when provided with a random photo and a painting to learn style from.

“Here we introduce an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality,” the paper says. “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.”

Check out many more examples via the article.


7 thoughts on “Neural algorithm makes photos emulate famous paintings

          1. … wrong place at the wrong time …? My cohort got the scheme to work in circa 2009 code – they may revisit it now (in GPU).

  1. Yes Replace Color does a nice job of matching colors and not likely used much since its tucked away in the menu list. And then there’s the Neutral check-box for another way to color balance, which is sometimes helpful.

Leave a Reply

Your email address will not be published. Required fields are marked *