Pixelmator Team always tries to extract the most out of iOS devices and macOS computers. The Pixelmator Photo, their app for iPads, is great and already bundles a lot of machine leaning in it. Now their latest ML-powered feature is called ML Super Resolution and it’s implemented on their macOS app, the Pixelmator Pro.
The app already provide three algorithms to scale an image: Bilinear, Lanczos and Nearest Neighbor; but they were using traditional mathematics calculations to predict pixels around. The ML Super Resolution comes to push scaling a little bit farther, analyzing the content of the image instead.
Until now, if an image was too small to be used at its original resolution, either on the web or in print, there was no way to scale it up without introducing visible image defects like pixelation, blurriness, or ringing artifacts. Now, with ML Super Resolution, scaling up an image to three times its original resolution is no problem at all.
It also requires more power from the computer and it was only possible to reasonably make it available to the end user in the last couple of years.
Naturally, the machine learning way requires a lot more processing power than the primitive approaches — between 8 to 62 thousand times more, in fact.
Making this available in an app like Pixelmator Pro has only become possible in the last couple of years — even on Mac computers from 5 or so years ago, ML Super Resolution can take minutes to process a single image due to slower performance and less available memory. On the latest hardware, however, images are processing in a few seconds, and even faster on iMac Pro, Mac Pro, or any Mac with multiple GPUs thanks to our use of Core ML 3 and its multi-GPU support. For the same reasons, the performance of ML Super Resolution is also significantly improved when using an eGPU.
If some details are somehow introduced with the optimized versions of the original image, it doesn’t matter as long as the final result is good enough and you can’t trace it back to the original file.