No Result
View All Result
Thursday, February 25, 2021
Chinese (Simplified)EnglishFrenchGermanItalianJapanesePortugueseRussianSpanish
Near future
  • Home
  • Tech
  • Medicine
  • Society
  • Environment
  • Spazio
  • Transportation
  • Weather
  • concepts
  • H+
Near future
No Result
View All Result

Covid-19 Updates »

June 13 2020
in Technology

Pulse, the GAN strikes again: from blurred pixels to HD photos

Chinese (Simplified)EnglishFrenchGermanItalianJapanesePortugueseRussianSpanish

Collaborate!

We are open to visions about the future. Submit an article, disclose the results of a search or scientific discoveries, shows points of view on a theme, tells about a change.

CONTACT US
pulse GAN
Share6Pin3Tweet4SendShare1
Gianluca Ricciodi Gianluca Riccio
4 minutes of reading
tags: AIPhotosGANartificial intelligence

The last

When there was Zoom 60 years ago: the history of the Picturephone

Coca-Cola, the world's largest plastic polluter, tests paper bottles

A Yale team repairs the spinal cord with patient stem cells

The autonomous drone to collect fruit thanks to AI

V90 Villa Edition, camper with terrace on the second floor

Pulse GAN, a neural network that with a revolutionary approach to images is able to increase the detail of blurred pixels up to 64 times as much.

Duke University researchers have developed an artificial intelligence tool that can turn blurry, unrecognizable images of people's faces into compelling computer-generated portraits, with finer detail than ever.

Methods prior to Pulse GAN could detail a pixelated image up to eight times its original resolution. But Duke's team devised a way to take a handful of pixels and create realistic-looking faces with up to 64 times the resolution, "imagining" features like fine lines, lashes and wrinkles that weren't in the first image. .

No images with this resolution have ever been created before

Cynthia Rudin, computer scientist, Duke University

It is not an identikit

The Pulse GAN system cannot be used to identify people, say the researchers: it will not turn a blurry and 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 seem plausibly real.

Maybe you are also interested

Hour One, the AI ​​that creates our talking and realistic digital clone.

Here's how AI can target our weaknesses to influence us

Machine learning now generates realistic genomes of people who don't exist

AI and Mental Health: Can Technology Digitize Psychologists?

The same technique could theoretically take low-resolution photos of almost everything and create sharp and realistic images, with applications ranging from medicine and microscopy to astronomy and satellite imagery, said the co-user Sachit Menon, double specialization in mathematics and computer science.

The researchers will present their method, called PULSE GAN, from tomorrow to June 19 at the 2020 Computer Vision and Pattern Recognition (CVPR) conference.

pulse GAN, from blurred pixels to HD photos
An example of a reconstructed photo

Traditional approaches start with capturing a low-resolution image with blurry pixels and "guessing" which extra pixels are needed by trying to match them, on average, to the corresponding pixels in high-resolution images that the computer has seen before. As a result of this averaging, textured areas in hair and skin that may not line up perfectly from pixel to pixel may appear blurry and indistinct.

The Duke team has taken a different approach

Instead of capturing a low resolution image and slowly adding new details, the system looks for examples of high resolution faces generated by AI (now become very good at this), looking for the ones that look as similar as possible to the input image when reduced to the same size.

The team used a machine learning tool called GAN, or 'adversary generative network'. I have talked about it more thoroughly in this article and others on this site. GANs are neural networks trained on the same photo dataset. One network features human faces created by artificial intelligence that mimic the ones it was trained on, while the other takes this result and decides whether it's compelling enough to be mistaken for a real photo. The first network gets better and better with experience, until the second fails to distinguish. They compete with each other, in other words, and by competing they improve.

pulse GAN, from blurred pixels to HD photos

PULSE is capable of creating realistic looking images from noisy and poor quality inputs. From a single blurry image of a face it can emit an unlimited number of realistic possibilities, each of which looks subtly different.

Even given pixelated photos where the eyes and mouth are barely recognizable, “our algorithm does something about it. Something that traditional approaches cannot do ”. Word of the co-author Alex Damian, mathematician at Duke.

Pulse GAN, the "fantasy" in power

The system can convert a blurred pixel image, or a 16 × 16 pixel image to a 1024 x 1024 pixel image in seconds, adding more than a million pixels, similar to HD resolution. Details such as pores, wrinkles and strands of hair, imperceptible in low resolution photos, become sharp and clear in the computer generated versions.

The researchers asked 40 people to evaluate 1.440 images generated via PULSE GAN and five other resizing methods. Their judgment? A number on a scale of one to five. and Pulse GAN has done best of all. What's more, he scored almost equal to high-quality photos of real people.

See the results for yourself http://pulse.cs.duke.edu/.

Comment this post on all the social networks where Futuroprossimo.it is present ( Facebook, Instagram, Twitter, Telegram, Linkedin, Vkontakte, Flipboard )

The future of:

Artificial intelligence

OncoHost, artificial intelligence that can “design” oncological therapies

transhumanism

Regenerating therapy, we are now one step away: there are just 5 years left.

Super Gadgets

Retyre, zippered bike tires

Design

Marble Arch Hill, an artificial hill that gives London another point of view

Most read of the week

  • V90 Villa Edition, camper with terrace on the second floor

    V90 Villa Edition, camper with terrace on the second floor

    79 shares
    Share 31 Tweet 20
  • Emrod is about to test remote wireless power transmission

    50 shares
    Share 20 Tweet 13
  • Aging without old age: we can get there very soon

    27 shares
    Share 11 Tweet 7

The last

Vision problems or blindness: three fantastic technologies

Is life expectancy written in our DNA?

It is the hunt for the universal vaccine against all coronaviruses

The US Air Force tests a technology to heal wounds 5 times earlier

The Coral, modular indoor micro algae: wall superfood!

Next article
Ascento, bipedal robot but on wheels

Ascento, bipedal robot but on wheels

Futuroprossimo.it is an Italian resource of futurology opened since 2006: every day news about the near future. Scientific discoveries, medical research, prototypes, concepts and predictions about the future for free.

Tag

Environment Architecture Communication concepts Advice Energy Events Gadgets The future of yesterday The newspaper of tomorrow Medicine Military Weather Robotica Society Spazio Technology transhumanism Transportation Video

Categories

The author

Gianluca Riccio, copywriter and journalist - Born in 1975, he is the creative director of an advertising agency, he is affiliated with the Italian Institute for the Future, World Future Society and H +, Network of Italian Transhumanists.

Collaborate! Are you interested in writing a post on Futuroprossimo? Click here for contacts.

Home / Author / IDEA / archive / Promo on FP

© 2020 Futuroprossimo - Tailored by Be Here

© 2020 Futuroprossimo - Tailored by Be Here

  • Home
  • Contact
  • archive
  • Technology
  • Medicine
  • Transportation
  • Weather
  • Society
  • Environment
  • transhumanism

© 2019 Futuroprossimo - Tailored by To be here

This site uses cookies. By continuing to read it, you consent to their use.