Now Reading
Google Artificial Intelligence That Sharpens Low Resolution Image

Google Artificial Intelligence That Sharpens Low Resolution Image

by Samuel OnyikeFebruary 8, 2017
You ever wondered if a poor image with that poor resolution can ever get better?
Well wonder no more.
The Brain team has developed a system that uses neural networks to fill in the details on very low-resolution images.

One of the networks is a “conditioning” element that maps the lower-res shot to similar higher-res examples to get a basic idea of what the image should look like. The other, the “prior” network, models sharper details to make the final result more plausible.

The result is not quite fro the record but can frequently come close to real deal. There is a room for upgrade i must say.
but amazingly a 8 pixel by 8 pixel image that bad has a recognizable facial features. The AI handling this is frequently close enough that you will at least have a spec of what is in the image.
Because of it’s present not so bad condition it is not recommended for a crime investigation,
but it could help validate hunches that their suspect was present in the background of a shot

Share what you just read.
What's your reaction?
Thumbs up
About The Author
Samuel Onyike
Epigrammatic tech-savvy writer. He loves to write on the ever changing technology topics and sees the human mind as the first virtual reality. Samuel doesn't need a manual to use a device even for the first time. He'll beat you in football games.

You must log in to post a comment