Adobe has also released a super resolution feature, but the results are, again, less dramatic. In our tests, the output from these sites was of a more mixed quality than Pixelmator’s (though it was generally good), and free users can only process a small number of images. There are a number of single-use super resolution tools online, including and LetsEnhance.io. The company isn’t the first to offer this technology commercially. ML Super Resolution utilizes machine learning (hence the ML in the name) and the processing power available in Apple iPad devices to enlarge photos. It’s trained on a range of images in order to anticipate users’ different needs, but the training dataset is surprisingly small - just 15,000 samples were needed to create Pixelmator’s ML Super Resolution tool.
It’s just 5MB in size, compared to research algorithms that are often 50 times larger. Pixelmator’s creators told The Verge that their algorithm was made from scratch in order to be lightweight enough to run on users’ devices. Then when it’s shown a low-resolution picture it’s never seen before, it predicts what extra pixels are needed and inserts them.
The algorithm compares this data and creates rules for how the pixels change from image to image.
In each case, the software is trained on a dataset containing pairs of low-resolution and high-resolution images. Research into super resolution has been ongoing for some time now, with tech companies like Google and Nvidia creating their own algorithms in the past few years. The algorithm learns to predict new details pixel by pixel