say i had so much footage, and I manually (tediously) went through it and separated all the objects from each other and said what they were doing. Then, I could take these words and then generate images using words. Then all you would need is symbolic ai and you could generate logical sequences of images, puzzled together out of different bodies. so you could get cleverbot, and get it to generate images for what it said, (if it spoke in descriptions rather than just chat replies) or maybe it plays sharades as it talks.
The best symbolic ai to date is watson, and im just wondering about perhaps giving it a dreaming ability? out of a puzzle of sprites.
Its a pretty easy idea to mention, but hard to implement, of course, but I dont see why it wouldnt work, then you could have a watson ai as a game mediator, and if you had enough footage, then the game visual could be quite varied.
I think if you went for shapes it might be interesting, as long as it could handle some variations in the shapes. Like getting it to recognize apples in different pictures.
Doing something like "please draw an image of an apple on a table", would be easy.
A lexical parser to seperate out the various elements of the sentence, a database of known objects, blah blah.
If that's what you want, I reckon you could do it and it would be fast enough on even a basic laptop.
However how far are you willing to go?
I want an image of the event horizon of a black hole viewed from inside the black hole in 4 space
Or the more likely end use....
me wAnT pic Holly Valance naKeeeeeDDDDD
Or some other brain dead user input.
actually that last one would be worth a lot of money..... maybe this could be a worthwhile project ;>