Alphabet's DeepMind Makes a Key Advance in Computer Vision

Alphabet's DeepMind neural networks can grasp a three-dimensional scene from just a handful of two-dimensional snapshotsImage: DeepMind
Researchers at Alphabet’s DeepMind today described a method that they say can construct a three-dimensional layout from just a handful of two-dimensional snapshots.
So far the method, based on deep neural networks, has been confined to virtual environments, they write inScience magazine. Natural environments are still to