Researchers from group Google Brain taught artificial intelligence to increase the resolution of the image restoration parts
Scenes from the movies when the image from the surveillance camera can zoom almost infinitely, getting more and more new details, still evoked a smile. However, a team of Google Brain managed to get a result, which makes these scenes more realistic.
The researchers reduced the original image size of 32 x 32 pixels to a size of 8 x 8. Then the neural network is formed based on these new image sizes to 32 x 32 pixels. This was recreated details that give the new images, enough similarity with the original images.
In fact, processing two of the network. One selects elements that are the most likely for a processed image, and the second simulates the details, sharpening to get the final result.
Of course, between the original images and results of the work of artificial intelligence there is a difference, however, in certain applications of the technology can be found now — for example, the increase of images, saving detail in cases where the accuracy of the result is not critical.