VIDEO: YOU CAN NOW FAKE YOUR OWN DANCE MOVES

Artificial Intelligence is helping out quite a lot these days, and it can now even assist with a way to fake your dance moves.

Deepfakes have been the most visible example of face-swapping peoples faces onto existing videos, but now it is here to deepfake your dance moves; it uses AI to read someone's dance moves and copy them on to a target body. The actual science here was done by a quartet of researchers from UC Berkely.

As they describe, in a paper posted on arXiV, their system is comprised of a number of discrete steps. First, it takes a video of the target that's recorded, and a sub-program turns their movements into a stick figure. (Quite of a lot of video-footage is needed to get a good quality transfer; around 20 minutes of footage at 120 frames per second.) 

Then a source video is found and a stick figure made of their movements. Then the swap happens, with a neural network synthesizing video of the target individual based on the stick figure movements of the source. It kind of sounds simple, but there is a lot of clever engineering work involved here. For example, there is a subroutine that smooths the movement of the stick figure so the dancers don't jerk about too much, and a completely separate neural network dedicated to re-tracing the target's face to ensure realism.

There are some limitations to the program. The network can't accurately model loose fabrics, for example, so the target individual has to wear tight-fitting clothes. In the video below, you can also see quite a few visual anomalies; moments where the joints of the target and source dancer don't quite line up, or where the AI software couldn't reproduce complex movements, like a hand flipping from back to front.

Still, it is impressive work. It is the sort of video manipulation that would probably take a whole team a few days to produce. Now, all it takes is some source video, and the right AI software. Expect it to be turned into an app before too long, and just don’t think about the possible implications about what technology like this will do to our trust of video evidence.