What’s New at the Samsung AI Lab? Animated Videos From a Picture

How to transform still photos into moving images?  


You know we are always on the hunt for crazy-smart innovations from the world of photography. This tops our list. Thanks to the Samsung AI Labs, they have created a fun way to turn a single photograph into a moving video.



First, you could “puppet” or morph anyone’s face using “Deepfakes” technology onto another person’s body–using a single photo for reference. Now you can create motion from a photograph. Learn and study a photo to learn movement. One shot learning from a single frame is possible, but if you have a series of similar pictures, the results are enhanced.




Excerpt from Devin Coldewey, writer & photographer at Fast Company:


Machine learning researchers have produced a system that can recreate lifelike motion from just a single frame of a person’s face, opening up the possibility of animating not just photos but also paintings. It’s not perfect, but when it works, it is — like much AI work these days — eerie and fascinating.

 


 

The model is documented in a paper published by Samsung AI Center, which you can read here on Arxiv. It’s a new method of applying facial landmarks on a source face — any talking head will do — to the facial data of a target face, making the target face do what the source face does.


Thanks to Samsung Electronics for this smart Artificial Intelligence (AI) innovative developed from its C-Lab (Creative Lab). Imaging from the 600 million pictures digitized at ScanMyPhotos.com — for people around the world — what they can now do to make their nostalgic memories pop and transform back to life?