MIT researchers develop neural network that recovers clear information from blurry images

Cal Jeffrey

TS Evangelist
Staff member

Researchers at MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL) trained the CNN by scanning thousands of pairs of images (projections) — one of low quality and the other the source (signal) of the blurry picture. The neural network uses the information to essentially reverse engineer the blurring effects by learning the pixel patterns and what created them.

Another part of the CNN, called a “variational autocoder,” analyzes the output and evaluates how well the network matched the signal. It then creates a “blueprint” to tell the AI how to go from a projection to all possible matching sources. When given a fresh image, the CNN examines the pixel patterns and uses the blueprint to find every possible signal that could have created the blurring. From there, it combines the data to create a “high-dimensional” copy.

"If we can convert X-rays to CT scans, that would be somewhat game-changing."

For example, in a video that shows a car speeding by, you might be able to tell that the car was red, but not much else. The visual deprojection model could take that footage and create a reproduction that is clear enough to identify the make and model.

“It’s almost like magic that we’re able to recover this detail,” said CSAIL postdoc Guha Balakrishnan, lead author of the paper.

Example aside, the researchers are more excited about what it could do in the medical field. They believe that the technology could be used to created 3D scans similar to CTs from X-rays. This breakthrough could significantly reduce costs since MRI and CT machinery is extremely expensive. The software would be able to recreate a high-information image from a low-information image like X-rays, which are comparatively inexpensive.

“If we can convert X-rays to CT scans, that would be somewhat game-changing,” said Balakrishnan. “You could just take an X-ray and push it through our algorithm and see all the lost information.”

Permalink to story.

 

VitalyT

Russ-Puss
That's how they catch that flash guy.

Seriously, the police used to throw away a lot of pictures with reg numbers blurred due to extreme speeding, and some crazy drivers used to take advantage of it, knowing that most cameras were unable to take a usable picture of a vehicle exceeding 300km/h. Now things may change there.

It wasn't so much a problem in the past. But today you can even buy a tuned up VW Golf R that can reach 300km/h :)
 
Last edited:

Uncle Al

TS Evangelist
It will be interesting to see this one in court. As the law stands "altered" photo's and video's are not submissable as evidence because they have been tampered with. The police and prosecutors will have to provide proof that they have altered these only for the good and not "beyond a reasonable doubt". I would predict this one will get quite a bit of play, especially when the ACLU gets involved .....
 
  • Like
Reactions: Yynxs

Yynxs

TS Addict
I am reminded of an article somewhere in my time about bubble wrap creating x-rays when popped. There was some speculation that it could be used in rugged Africa where x-ray machines were not available or could not be easily transported.

If the AI involved can be reduced to a phone and phone camera (or phone physical add-on application) and be pointed at that sort of situation where 'the cloud' doesn't exist, then this is a cause for some excitement.
 

Latest posts