New algorithm “enhances” low-res photos till they are tack sharp in hi-res
Nov 1, 2017
Dunja Đuđić Kalinin
Dunja Djudjic is a multi-talented artist based in Novi Sad, Serbia. With 15 years of experience as a photographer, she specializes in capturing the beauty of nature, travel, concerts, and fine art. In addition to her photography, Dunja also expresses her creativity through writing, embroidery, and jewelry making.
Share:
The scientists of Max Planck Institute for Intelligent Systems in Germany have developed a new algorithm. It enhances low-res images so that they miraculously become hi-res and sharp. It only needs a single low-resolution input, and it will increase its resolution while retaining the realistic textures and details.
According to the paper, the existing algorithms don’t perform the resolution enhancement so well. They tend to produce images that are too smooth and lack realistic textures, so they look unnatural. So, the scientists have created the algorithm that focuses on producing realistic textures.
The researchers used a large set of images to train the neural network. They fed the neural network hi-res photos, so it “learns” to recognize different textures. Then they’d input low-res images, and the algorithm would upsample them. The researchers would then compare the results and adjust the algorithm further to fix the errors. As a result, they have produced an algorithm that makes all those scenes from CSI series look like they’re actually possible.
Of the researchers, Mehdi M.S. Sajjadi, tells Digital Trends this algorithm could have many different applications. You can use it to upsample old movies to 4K quality or restore old family photos. As for more general applications, it can also be used to improve object detection. Sajjadi points out their algorithm could also make it “it easier for other neural networks to detect objects in images.” This could be applied to situations “from Google image search to detecting pedestrians in self-driving cars.”
When it comes to upsampling low-res images, Google has also created a solution for this. It’s even implemented into Google+ for Android, in order to save bandwidth. Other than this, artificial intelligence has had some useful (or just fun) uses in photography so far, and its applications will most likely continue to grow. If you’d like to read more about the latest image enhancing algorithm and see some sample images, you can read the full paper here.
[via Digital Trends]
Dunja Đuđić Kalinin
Dunja Djudjic is a multi-talented artist based in Novi Sad, Serbia. With 15 years of experience as a photographer, she specializes in capturing the beauty of nature, travel, concerts, and fine art. In addition to her photography, Dunja also expresses her creativity through writing, embroidery, and jewelry making.
Join the Discussion
DIYP Comment Policy
Be nice, be on-topic, no personal information or flames.
29 responses to “New algorithm “enhances” low-res photos till they are tack sharp in hi-res”
Help for Canon users has arrived! ;)
Hahahaha
if it works for video, then help for nikon users has arrived :D
Unfortunately, this will not work for Nikon users. They are beyond help.?
For those of you who like to steal online images…
CSI called it ?
Unlikely, but okay…
tried it, works like a charm
#FullOfCrap
seems legit
Chris Brock #noshit
1 April
so wait….we finally have the “enhance the image” feature from CSI? We’re truly living in the future
Nope… As they said, it can guess which texture belongs somewhere and apply that. But it can’t add missing details. It might even add a wrong face to a person in a low res picture because there is no such thing as magic in there.
Well, it is certainly quite impressive what well used maths can do, but the “Ihr” images at the right of the article series are the hi-res originals, not reconstructions…
Let’s just say it right – it CLAIMS to enhance, since it is still just a reseqrch paper… And let’s present a real article here, rather than clickbait, @DYIPhotography ?
I’ll be waiting. How and where to test it, if available?
omg the zoom and enhance joke is no longer a joke.
NO WAY. You cannot capture detail that was not available in the “original” digital file.
Ever heard of interpolation? You don’t even capture the ‘real photo’ while you take a snap shot. You take a down sampled digitalized array of pixel data. If you have two reference point, you can make an ‘educated’ guess with the help of mathematics. That educated guess can have a correlation factor 1 if implemented correctly. So this is actually very much possible.
The algorithm is apparently taking an educated guess at what the detail texture would be.
All the Graphic Artists will be happy to hear that, one of the most annoying request from clients.
so people can now upsize your low rez photos that you uploaded online, and they’ll be able to print your images from their printer without you knowing that you have prints somewhere, or are they trying to be able to upsize images from mobile phone DSLR for big prints?
so people can now upsize your low rez photos that you uploaded online, and they’ll be able to print your images from their printer without you knowing that you have prints somewhere, or are they trying to be able to upsize images from mobile phone to match DSLR for big prints?
…heaven forgive, actually learning to use your camera and focusing properly to begin with… This sort of ‘techno’ crap will soon turn the ‘art of photography’ into a totally valueless endeavour !
just another way for people to steal you work off line :(
That was my first thought, too. :-(
Is it April 1st already? ?