I've seen this effect done to a single still image before, but presumably it was done by hand somehow. Specifically, in the “Kony 2012” video (remember that?)
The effect itself is actually not too uncommon. It is just very tedious and time-consuming to do manually since it requires segmenting the elements in the scene, arranging them in a 3D space, filling in any holes and specifying a virtual camera trajectory.
Thanks for clarifying this. My roommate used to do this in after effects 10 years ago, so I couldn't understand what the demo video was attempting to showcase.