A machine-learning model for high-resolution computer vision could enable computationally intensive vision applications, such as autonomous driving or medical image segmentation, on edge devices.

A team of researchers at MIT CSAIL, in collaboration with Cornell University and Microsoft, have developed STEGO, an algorithm able to identify images down to the individual pixel.

NN = nearest neighbour (looking for a high-res image in the dataset that closely matches the 8x8 image) Google Brain Google Brain Various different super-resolution techniques.

High-quality graphics cards can significantly improve the visuals on your favorite computer games. La Bicicleta Vermella/Getty Images ...

Incredible new images of the sun's surface provide an unprecedented view of raging sunspots and solar activity. A new high-resolution camera system developed by the Leibniz Institute for ...

He also hints that the technology could be adapted to create better digital zooming. Super Resolution uses machine learning to alleviate most of the blurriness that comes with upscaling an image.