Hey guys!
I have a ideia em mind but i don't know if will help, so I would like same help, I'll try to describe to you.
Basically the software will get the layers of images and "transform" into 3d objects, so for example, a image with "3" layers (a person in front a car and a house in the background) in this case, the person will be in the height 3x, the car heights 2x and the house heights x. For each layer we will have sub heights according each color, black will keep on x (for the house) and most close to white will be a little higher let's say 1.75 x.
if we transform, let's say, a comic book in this object, do you think will be able to understand what is happening in the scene? If while you are touching the scene you are listening the dialog.
I don't know if I was clear.
Thanks a lot for the help guys!