Reported today on The Verge For the full article visit:
Reported today in The Verge.
AI super resolution lets you 'zoom and enhance' in Pixelmator Pro
The "zoom and enhance" trope is a TV cliché, but advances in AI are making it a reality. Researchers have shown that machine learning can enlarge low-resolution images, restoring detail that wasn't there before. Now, this technology is making its way to consumers, with image editor Pixelmator among the first to offer such a feature.
The Photoshop competitor today announced what it calls "ML Super Resolution" for the $60 Pro version of its software: a function that the company says can scale an image up to three times its original resolution without image defects like pixelation or blurriness.
After our tests, we would say this claim needs a few caveats. But overall, the performance of Pixelmator's super resolution feature is extremely impressive.
Pixelation is smoothed away in a range of images, from illustration to photography to text. The results are better than those delivered by traditional upscaling algorithms, and although the process is not instantaneous (it took around eight seconds per image on our 2017 MacBook Pro), it's fast enough to be a boon to designers and image editors of all stripes.
Take a look at the example below, with the low-resolution image on the left and the super resolution version on the right. It's easy to see how the tool has smoothed out the blurry text and bones of the skeleton:
Here's another section of the same image. Again, the difference is dramatic, but the drawbacks of super resolution are also more obvious. The processed image is smooth and cartoony, with an almost plasticine feel to the edges.
If we apply super resolution to a photo portrait, the defects become more noticeable, especially in a zoomed-in image like the one below. In t
0 Comments