I always chortled when the Good Guys were looking at some grainy surveillance footage and they “enhanced” the image to read a license plate. But it’s a major research area – self-driving cars – and a new paper takes image super-resolution, the term of art, to a new level. See the picture after the jump.

In new paper, href=”” target=”_blank”>=”https://arxiv.org/pdf/1809.00219.pdf” target=”_blank”>ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks, researchers demo some amazing results.

.

The StorageMojo take
The problem with making stuff up to create details that can only be inferred from the original is noted by the researchers: “. . . hallucinated details are often accompanied with unpleasant artifacts.” As Morpheus might say, “I know exactly what you mean.” Trippy!

Courteous comments welcome, of course.