This is pretty amazing.
Especially as at this stage it is an early proof of concept.
Make sure you check out the video, the description and the thumbnail does NOT do it justice:
We reconstruct 3D photos from casually captured cell phone or DSLR images: a panoramic, textured, normal mapped, multi-layered geometric mesh representation, that can be viewed with full binocular and motion parallax in VR, as well as with a regular mobile device or web browser.
So basically, you can capture a three dimensional scene, in a manner as easy as taking a panoramic photograph, and then navigate, add lighting or special effects, to the rendered scene.
What do you think this could be used for?
There are obvious things like tourism and real estate ...
I was thinking maybe capturing crime scenes?
All images from the whitepaper