Training artificial neural networks with data from real brains can make computer vision more robust.

MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.

This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.

A new computer vision system turns any shiny object into a camera of sorts, enabling an observer to see around corners or beyond obstructions.

Researchers identify a property that helps computer vision models learn to represent the visual world in a more stable, predictable way.

A new method could provide detailed information about internal structures, voids, and cracks, based solely on data about exterior conditions.

By keeping data fresh, the system could help robots inspect buildings or search disaster zones.

The device could help workers locate objects for fulfilling e-commerce orders or identify parts for assembling products.

Computer scientists want to know the exact limits in our ability to clean up, and reconstruct, partly blurred images.

Dan Huttenlocher is a professor of electrical engineering and computer science and the inaugural dean at MIT Schwarzman College of Computing.