Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5

Artificial intelligence makes blurry faces look more than 60 times sharper

#1
C C Offline
https://today.duke.edu/2020/06/artificia...es-sharper

RELEASE: Duke University researchers have developed an AI tool that can turn blurry, unrecognizable pictures of people’s faces into eerily convincing computer-generated portraits, in finer detail than ever before. Previous methods can scale an image of a face up to eight times its original resolution. But the Duke team has come up with a way to take a handful of pixels and create realistic-looking faces with up to 64 times the resolution, ‘imagining’ features such as fine lines, eyelashes and stubble that weren’t there in the first place.

“Never have super-resolution images been created at this resolution before with this much detail,” said Duke computer scientist Cynthia Rudin, who led the team. The system cannot be used to identify people, the researchers say: It won’t turn an out-of-focus, unrecognizable photo from a security camera into a crystal clear image of a real person. Rather, it is capable of generating new faces that don’t exist, but look plausibly real.

While the researchers focused on faces as a proof of concept, the same technique could in theory take low-res shots of almost anything and create sharp, realistic-looking pictures, with applications ranging from medicine and microscopy to astronomy and satellite imagery, said co-author Sachit Menon ’20, who just graduated from Duke with a double-major in mathematics and computer science. The researchers will present their method, called PULSE, at the 2020 Conference on Computer Vision and Pattern Recognition (CVPR), held virtually from June 14 to June 19.

Traditional approaches take a low-resolution image and ‘guess’ what extra pixels are needed by trying to get them to match, on average, with corresponding pixels in high-resolution images the computer has seen before. As a result of this averaging, textured areas in hair and skin that might not line up perfectly from one pixel to the next end up looking fuzzy and indistinct.

The Duke team came up with a different approach. Instead of taking a low-resolution image and slowly adding new detail, the system scours AI-generated examples of high-resolution faces, searching for ones that look as much as possible like the input image when shrunk down to the same size. The team used a tool in machine learning called a “generative adversarial network,” or GAN, which are two neural networks trained on the same data set of photos. One network comes up with AI-created human faces that mimic the ones it was trained on, while the other takes this output and decides if it is convincing enough to be mistaken for the real thing. The first network gets better and better with experience, until the second network can’t tell the difference.

PULSE can create realistic-looking images from noisy, poor-quality input that other methods can’t, Rudin said. From a single blurred image of a face it can spit out any number of uncannily lifelike possibilities, each of which looks subtly like a different person. Even given pixelated photos where the eyes and mouth are barely recognizable, “our algorithm still manages to do something with it, which is something that traditional approaches can’t do,” said co-author Alex Damian ’20, a Duke math major.

The system can convert a 16x16-pixel image of a face to 1024 x 1024 pixels in a few seconds, adding more than a million pixels, akin to HD resolution. Details such as pores, wrinkles, and wisps of hair that are imperceptible in the low-res photos become crisp and clear in the computer-generated versions. The researchers asked 40 people to rate 1,440 images generated via PULSE and five other scaling methods on a scale of one to five, and PULSE did the best, scoring almost as high as high-quality photos of actual people.

See the results and upload images for yourself at http://pulse.cs.duke.edu/.
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Quotes about Artificial Intelligence Magical Realist 29 847 Jan 3, 2024 10:25 AM
Last Post: stryder
  Article Artificial intelligence: Four debates to expect in 2024 C C 0 49 Jan 3, 2024 02:01 AM
Last Post: C C
  Article A new approach to computation reimagines artificial intelligence C C 1 76 Apr 15, 2023 08:44 AM
Last Post: Kornee
  Article Artificial intelligence finds the first stars were not alone C C 0 48 Mar 27, 2023 07:14 PM
Last Post: C C
  The danger of advanced artificial intelligence controlling its own feedback C C 0 141 Oct 25, 2022 08:21 PM
Last Post: C C
  How artificial intelligence can explain its decisions C C 0 127 Sep 3, 2022 10:37 PM
Last Post: C C
  Will transformers take over artificial intelligence? C C 0 78 Mar 11, 2022 07:24 PM
Last Post: C C
  Consciousness in humans, animals and artificial intelligence C C 0 98 Dec 21, 2021 09:41 PM
Last Post: C C
  Artificial Intelligence that can discover hidden physical laws in various data C C 0 60 Dec 11, 2021 05:08 AM
Last Post: C C
  New report assesses progress and risks of artificial intelligence C C 0 73 Sep 17, 2021 01:58 AM
Last Post: C C



Users browsing this thread: 1 Guest(s)