- Maybe we should start taking Tom DeLonge seriously about UFOs 3 Years Ago
- Get ready to argue about the alternate-history politics of HBO’s ‘Watchmen’ Today 8:53 AM
- Third instance of Justin Trudeau wearing racist makeup emerges after he apologized for first 2 Today 8:45 AM
- 6 must-watch college football games to stream this weekend Today 8:12 AM
- What is the Hinge dating app, and how does it work? Today 7:00 AM
- ‘Inside Bill’s Brain’ is nothing more than a Bill Gates infomercial Today 6:30 AM
- Swipe This! He hasn’t texted me back. Should I text him again? Today 6:00 AM
- New Loch Ness monster video may just confirm giant eel theory Wednesday 8:04 PM
- Instagram to restrict posts promoting diet culture and plastic surgery Wednesday 6:58 PM
- Apple wants to trademark ‘Slofie,’ its term for slow-motion selfies Wednesday 5:51 PM
- Fortnite leak reveals a Batman crossover event may be happening Wednesday 5:32 PM
- The explosion at a bull semen factory generated a lot of obvious jokes Wednesday 4:33 PM
- Jessica Jaymes, adult film star, dead at 43 Wednesday 4:18 PM
- How to stream Falcons vs. Colts in Week 3 Wednesday 4:05 PM
- Beto O’Rourke says he opposes police use of facial recognition tech Wednesday 4:01 PM
On television, this image enhancer is called “zoom in, enhance,” an age-old trope that usually shows our hero unrealistically taking a blurry image, zooming in on it, and enhancing the details in order to catch the “bad guy.”
In engineering that method is called super-resolution imaging, and it is achieved by teaching a neural network, or a computer modeled on the human brain. The computer will look for certain details in the original image and fill in the gaps with hallucinations—data added using the computer’s knowledge about typical facial features.
The results are pretty incredible.
In the capture above, you have an unrecognizable low-resolution image on the left, the computer-enhanced image in the middle, and the real image on the right.
While some of the computer’s creations may look terrifying, the accuracy and amount of detail gathered from the indistinguishable 8×8 image is astonishing.
The computer-generated images were accurate enough to fool a test audience. People were asked to choose which picture they thought was the “ground truth.” They chose Google Brain’s super-resolution image in about 10 percent of the celebrity examples, and 28 percent of the bedroom examples.
That level of accuracy could be used to give law enforcement a better idea of how a suspect might look, but is still a long way away from being able to make any conclusive decisions.
H/T Ars Technica
Phillip Tracy is a former technology staff writer at the Daily Dot. He's an expert on smartphones, social media trends, and gadgets. He previously reported on IoT and telecom for RCR Wireless News and contributed to NewBay Media magazine. He now writes for Laptop magazine.