© Screenshot: Chung-Yi Weng/YouTube
The latest of these is a project created by researchers from Facebook and the University of Washington called Photo Wake-Up. Photo Wake-Up combines AI in the form of machine vision and both augmented and mixed reality to do something really quite extraordinary: it detects figures in paintings, photographs, or other images, isolates them, and then animates them, making them appear to leave their 2-D surface.
Yes: it's another nail in the Flatweb's coffin and it couldn't have come at a better time.
The creators discussed their methodology in a paper last December, describing how their "method not only enables new ways for people to enjoy and interact with photos, but also suggests a pathway to reconstructing a virtual avatar from a single image." Such a feat would be the equivalent of the well-known scene in Star Wars: A New Hope where Leia appears via hologram to Luke Skywalker and Obi-Wan Kenobi.
"We present a method and application for animating a human subject from a single photo. E.g., the character can walk out, run, sit, or jump in 3D. The key contributions of this paper are: 1) an application of viewing and animating humans in single photos in 3D, 2) a novel 2D warping method to deform a posable template body model to fit the person's complex silhouette to create an animatable mesh, and 3) a method for handling partial self occlusions. We compare to state-of-the-art related methods and evaluate results with human studies. Further, we present an interactive interface that allows re-posing the person in 3D, and an augmented reality setup where the animated 3D person can emerge from the photo into the real world. We demonstrate the method on photos, posters, and art."
Take a look for yourself.
This is why the Greys have such big eyes - they're wearing VR technology...
...and full wearable technology from top to toe, replaced daily.
...this is why the species is in it's twilight...
It's us...