Forgot your password?



Back to login

Neural Network gives smartphone snaps professional look
November 6, 2017, 3:17 pm
Share/Bookmark

Scientists at the ETH Zurich Computer Vision Lab in Switzerland recently published a paper describing a deep learning approach that uses neural networks to translate photos taken by cameras with limited capabilities such as those found in many smartphones into high-quality photos automatically.

Generational Adversarial Networks (GAN) is a new type of algorithm that uses two or more neural networks to compete against each other to raise the quality of photos, or even videos.
Researchers in Zurich provided GAN with two data sets — one made up of images from a phone camera, the other composed of high-quality photos. Then they used several neural networks to bring the quality of the phone photos up to that of the high-quality images captured with a DSLR.

What the researchers are doing is in line with what photographers have been doing for ages in photography darkrooms or more recently with photo-editing software, such as Photoshop or Gimp. The new method put forward by researchers in Zurich basically automates the whole process of taking a not-so-great photo and rendering it to a much higher quality.

However, many serious photographers would disapprove of the changes made to the photos on the researchers' samples page. Technically, the changes added a lot of contrast but lost some detail in the process, which would make them inferior to what a professional photographer would produce. This is perhaps a good example of how technology can be used to improve the baseline of what is acceptable. The program can only improve upon the data that is already available in the photo, so the better the quality of input data the better the result will be.

But as the processing power in smartphones increase and the software keeps getting better, mobile devices could soon begin to pose a threat to camera makers; already the point-and-shoot cameras are being replaced by many smartphone.

Share your views
CAPTCHA
 

"It is hard to fail, but it is worse never to have tried to succeed."

"Envy comes from wanting something that isn't yours. But grief comes from losing something you've already had."

Photo Gallery