Google’s DeepMind AI is pretty awesome, and can do a lot of things, One of the latest things it “learned” is to create 3D models from only observing 2D pictures.
Given just a handful of pictures of a scene — a wallpapered room with a colored sphere on the floor, for example — the algorithm can render opposite, unseen sides of objects and generate a 3D view from multiple vantage points, even accounting for things like lighting in shadows.
It can do all of this without any human intervention, as it “imagines” the 3D scene.
It was not easy, though. Researchers fed the system images of various scenes from different angles, which was used to teach the system about textures, colors, lights…
Subscribe to our newsletter
Of course, the system is still very limited, as it can generate simple scenes with a limited amount of simple 3D models. Still, it will be interesting to see how the technology progresses.