Realistic images generated by AI neural networks are all the rage at the moment. Images like these AI generated Duke Nukems(opens in new tab) have gone viral for their disturbing yet weirdly accurate takes. While AIs like DALLE-2 can make photoshop magic better than the real thing(opens in new tab), all of this is about to get much crazier as it moves to 3D.
GAN is one such popular machine learning model(opens in new tab) that pits two neural networks against each other to help make more accurate predictions. It's already proven effective for 2D image recreation and according to MarketTechPost (opens in new tab)researchers at Stanford have put it to work creating powerful 3D images.
The researchers have called the AI model EG3D, and takes high resolution 2D GAN images and moves them into the 3rd dimension. It does this in a manner that is far less computer intensive and more accurate than previous attempts, and even boasts being able to manage this on laptop machines. Though Github(opens in new tab) does recommend 1-8 high-end Nvidia GPUs, so maybe make that a fairly good laptop to get the job done.
This seems to be largely achieved by the AI's neural networks being trained in the resulting topography from 2D images until a consistent result is achieved. This has led to the team producing some creepily real pictures of people's faces from multiple angles. It has also created some very cute pictures of cats which feels much less threatening.
Best gaming PC(opens in new tab): The top pre-built machines from the prosBest gaming laptop(opens in new tab): Perfect notebooks for mobile gaming
The biggest downside with these creations is they can be difficult to edit and refine. Thanks to being produced by AI, they aren't
Read more on pcgamer.com