Google has just announced an image compression method that is revolutionary in more ways than one. Basically it relies on an AI algorithm to invent the parts of the image that aren’t actually there.
AI upscaling or super-resolution is an interesting, and almost magical, technique that we have looked at before.
The basic idea is that images are highly redundant and, given a low resolution image, a human can perform a better upscaling than simply using image statistics. By knowing that the fuzzy blob is in fact a face, the human can make the features more distinct where most statistical interpolation methods improve the resolution but often blur the image even more.
You can see that the image on the right has more pixels, but it is blurred by comparison with the blocky low res image. You could probably do better by taking a tool that sharpens the obvious edges.
If a human can do it then so can AI. Google introduced an AI upscaling program called RAISR back in November 2016. It learns filters that essentially sharpen the image from a set of images and lower resolution images derived from them.
« With RAISR, we instead use machine learning and train on pairs of images, one low quality, one high, to find filters that, when applied to selectively to each pixel of the low-res image, will recreate details that are of comparable quality to the original. RAISR can be trained in two ways. The first is the « direct » method, where filters are learned directly from low and high-resolution image pairs.
