Adobe Lightroom and Camera Raw now use AI to enhance details in your photos

Adobe has been using its AI-powered Sensei technology to introduce various upgrades to its apps. In the most recent upgrade, Camera Raw, Lightroom Classic, and Lightroom CC became able to enhance details in your images and give you up to 30% higher resolution on raw files.

The new feature is called Enhance Details and it uses machine learning to provide “state-of-the-art quality” for your images. Adobe explains that it approaches demosaicing in a new way, so it provides better resolving fine details and fixing issues like false colors and zippering.

Demosaicing process can be tricky if your image has some more regions: texture, fine details, repeating patterns, or sharp edges. In these cases, “standard demosaicing methods can struggle, producing lower resolution and problematic artifacts,” Adobe explains in a blog post. It is possible to handle these complicated areas, but the problem with the advanced methods is that they’re computationally expensive. This is where Enhance Details steps in, and Adobe explains how it works:

Enhance Details uses an extensively trained convolutional neural net (CNN) to optimize for maximum image quality. We trained a neural network to demosaic raw images using problematic examples, then leveraged a new machine learning frameworks built into the latest Mac OS and Win10 operating systems to run this network. The deep neural network for Enhance Details was trained with over a billion examples.

Each of these billion examples contained one or more of the major issues listed above that give standard demosaicing methods serious trouble. We trained two models: one for the Bayer sensors, and another for the Fujifilm X-Trans sensors.

Adobe promises that Enhance Details delivers higher resolution, more accurate rendering of edges and details, and fewer artifacts like false colors and moiré patterns. It’s worth noting that it works on both Bayer (Canon, Nikon, Sony, etc.) and X-Trans (Fujifilm) raw mosaic files.  However, there are some system requirements and things to take into consideration:

• Enhance Details requires Apple’s Core ML and Microsoft’s Windows ML. In other words, it won’t work on older operating systems, so you need to update to macOS 10.13 or Win 10 (1809) or later.
• Enhance Details requires intensive processing, and it can take some time to do its work.
• Faster GPU means faster results. An eGPU (external GPU) can make a big difference.

[image credits: Adobe]