Photoshop uses AI to quadruple the resolution of a photo without losing quality

Photoshop uses AI to quadruple the resolution of a photo without losing quality

Super Resolution is the new tool that the Photoshop team has presented and that has a great particularity.

This feature uses the full potential of artificial intelligence so that the user can quadruple the size of a photo without losing quality or detail along the way.

This is how Photoshop increases the original size of a photo without losing quality

As the Photoshop team explains, they have trained a neural network with millions of photos by alternating pairs of small cutouts of images in low and high resolution, covering different details and themes. In this way, the AI ​​learns to analyze pixels, to increase the size of images in low resolution, from a reference.

Here’s how, for example, you can convert a 10-megapixel photo to a 40-megapixel photo:

Zooming in on a photo often produces blurry details, but Super Resolution has an ace up its sleeve: an advanced machine learning model trained on millions of photos. Backed by this vast training suite, Super Resolution can intelligently enlarge photos while keeping edges clean and preserving important details.

In the examples of images shown on the Photoshop blog you can see how the photos maintain sharp colors and precision in details. And to get that result, the user will only have to use a few clicks and wait for the image to be processed.

Of course, it is not a function that can be applied to every photo we have in the library because of the resource requirements and size of the DNG file. But it can help us to obtain authentic jewels in those cropped images or when we have to present an important printing project.

This Enhance Super Resolution feature is now available in Camera Raw 13.2, and will be added in Lightroom and Lightroom Classic in the future.