Computer remixes famous film scenes with classical art
Computer vision researchers in Germany can transform video clips into the style of famous paintings.
Imagine that you could take any video clip and transform it into the art style of a classic painter with a click of a button. That's the process that researchers at Germany's University of Freiburg have been working on thanks to the advancement of computer learning. The team has learned that it's now possible for computers to watch the action on screen and effectively see the elements that make up each frame. It can then trace the outlines of, for instance, the actors in the foreground, and re-skin them with any art style you choose. For instance, the team took scenes from British TV series Miss Marple and made them look as if they'd been painted by Van Gogh during his Starry Night phase.
As you can see in the first video, some of the clips look no better than some of the images that come out of Google's DeepMind. Others, however, like the scenes from Cloud Atlas and the Jungle Book, seem significantly better-looking after being processed. It's still early days, but there are plenty of areas in both filmmaking and art where systems like this could be applied.
Right now, it's computationally intensive, but not so much that you can't expect the cost and availability of such power to drop. As MIT Tech Review explains, it takes three minutes for each frame to be processed on a system using NVIDIA's $1,000-plus Titan X graphics card. Given that Movidus' deep learning USB stick already costs less than $100 (and fits inside a USB stick), it seems likely that smart TVs of the future could have art-filtering as a feature within the decade.
