AI Is Learning How To Build Its Own Video Game Worlds

A team of researchers from the University of Lyon, Purdue and Ubisoft have published a paper showing what may well be the future of creating video game worlds: an AI that is able to construct most of its own 3D landscapes.

Similar to Nvidia’s work that is able to conjure its own celebrity mugshots, the tech would require only minimal input from a human, who would just have to contribute some basic requirements, draw some lines then let the AI do all the hard work: namely, filling in all the gaps with elevation, ridges and natural-looking rock formations.

As the paper states, this kind of tech would only be the beginning; future research could lead to landscapes being generated entirely by the AI, and for the model to be able to handle more complex environmental features like sand and vegetation.

Luke Plunkett is a Senior Editor based in Canberra, Australia. He has written a book on cosplay, designed a game about airplanes, and also runs

Share This Story

Get our `newsletter`



We’re always asking “can we?” but we rarely ask “should we?”. I mean - giant open world games have been getting boring and lackluster, and then we get Breath of the Wild, which is amazing specifically because of the massive attention to detail in lovingly handmade world.

We never care about size or scope in games like that, we care about content and quality. I guess the argument could be made that if they don’t have to “make” the world, they can spend more time populating it with stuff... But I feel there are gonna be a lot of devs who skip that part and just market the heck out of the scope (looking at you No Man’s Sky)