Adobe’s ‘Super Resolution’ Feature Can Make Your Images Pop

One of the first things you learn when you get into working creatively in a digital space is that resizing raster images bigger… doesn’t really work. You’re asking the computer to create more pixels where there aren’t any, so you lose image quality as you scale up.

With Adobe newest feature update to Camera Raw, that’s no longer the case.

ACR Now Gives You Bigger, Clearer Photos

Eric Chan, Michaël Gharbi, and Richard Zhang of Adobe Research have updated Adobe Camera Raw (ACR) with a groundbreaking new feature called “Super-Resolution,” which upsizes an image by a factor of four using AI.

Chan writes to the Adobe Blog:

Enlarging 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 set, Super Resolution can intelligently enlarge photos while maintaining clean edges and preserving important details.

It sounds too good to be true—especially if you’ve been rolling your eyes at TV crime dramas for their “unrealistic” technology—but Super Resolution is solving a problem that digital creatives have had to work around for years now.

Adobe's 'Super Resolution' Feature Can Make Your Images Pop

You can start using the feature in ACR version 13.2. It’s also confirmed to soon come to Lightroom and Lightroom Classic as well.

Super Resolution builds upon the “Enhance Details,” feature that Adobe released two years ago, which used machine learning to interpolate raw files with an uncanny degree of fidelity. “When you apply Super Resolution to a raw file, you’re also getting the Enhance Details goodness as part of the deal,” Chan says.

How Does Super Resolution Work?

To develop Super Resolution, Chan explains that the research team had to train a computer with millions of pairs of low and high resolution images. This allowed the computer to figure out how to upsize the low resolution ones.

Super Resolution follows a “deep convolutional neural network” structure, which really is just a fancy way of saying that in order to understand how to sample a pixel, the computer analyzes the other pixels surrounding it.

Adobe Catches Lighting in a Bottle… Again

The addition of Super Resolution to ACR feels a lot like when Adobe first unveiled PDF files in 1993. This is a revolutionary thing—the company is providing a new digital imaging solution that we all thought would never become a reality.

Once again, Adobe is proving why its products are the industry standard. Here’s where we believe the difference lies: while other competitors are focused on being a better version of Adobe, Adobe remains laser focused on doing what no one else has done yet.