Deep neural networks can now transfer the style of one photo onto another

This post was archived from a Google Plus post found here


From +Ninja On Rye​:

Style Transfer – now for photos

As Wayne remarks, many of us have seen the style transfer techniques applied by deep learning to paintings. This extends that to (the detail of) photos. Cool examples can be seen in the article.

For now, though, the researchers are already thinking about what areas photorealistic style transfer could be applied to next. “The question of how far you can push it is important,” says Bala. “Video is a logical thing for it to go to, and that, I expect, will happen.”

“You’ve probably heard of an AI technique known as ‘style transfer’ — or, if you haven’t heard of it, you’ve seen it. The process uses neural networks to apply the look and feel of one image to another, and appears in apps like Prisma and Facebook. These style transfers, however, are stylistic, not photorealistic. They look good because they look like they’ve been painted. Now a group of researchers from Cornell University and Adobe have augmented style transfer so that it can transfer the look of one photo onto another — while still looking like a photo.”

“Essentially, they’ve taken the methods of the original style transfer, and added another layer of neural networks to the process — a layer that makes sure that the details of the original image are preserved.”

https://www.theverge.com/2017/3/30/15124466/ai-photo-style-transfer-deep-neural-nets-adobe