Starting with yesterday’s post, I’d like to take a look at something waiting for us, right around the development corner.   Simply put, taking any number of images on any one thing, for instance several pictures of our president here in the United States, and loading them into the app/software and gaining 3D perspective and function.  The sole purpose, in this particular case, would be to be able to create new 2D images.

You take 2 or more pictures of the president, being from different perspectives, and load them into the software.  The software creates a 3D dataset for the image.  Then you pick your angle, click “render” and you get a brand new image of the president, that satisfies the following criteria –

1. It is from a brand new vantage, not necessarily supplied by the source images.
2. It is as detailed as the original source images, and would be humanly impossible to determine “created.”

This may hit your mind as a rather simple thing, but it has far reaching application.  Consider anytime you saw a well photoshopped image of perhaps a famous actor in some awkward situation, and you couldn’t tell it wasn’t a real photo.  This would be a lot easier to get away with if you could simply create any 2d angle of that particular persons face you wanted.  On a more troubling front, think of the value of photo evidence in criminal investigation, if images can simply be created out of thin air.