Super-resolution imaging is a class of techniques that enhance the resolution of an imaging system (Wikipedia). The entertainment series CSI has been ridiculed for relying on exaggerated and unrealistic applications of it:

Until recently, such upscaling of images were though near impossible. However, we have evidenced some pretty amazing breakthroughs in the deep learning space recently. Artificial Intelligence can think ahead, learn physics, and beat experts at their own games (DOTA; Poker), mostly through inventive applications of neural networks.

As a result, there are now several applications where machines have learned to literally fill in the blanks in imagery. Most notable seems the method developed by Google: Rapid and Accurate Image Super Resolution, or RAISR is short. In contrast to other approaches, RAISR does not rely on (adversarial) neural network(s) and is thus not as resource-demanding to train. Moreover, it’s performance is quite remarkable:

You can read more details in the paper by Romano, Isodoro, and Milanfar (2016) or watch the research summary below by, unsurprisingly, Two Minute Papers:

I guess you’re eager to test this super resolution out yourself?! letsenhance.io let’s you enhance the resolution of five images for free, after which it charges you $5 per twenty pictures processed. The website feeds the input image to a neural net and puts out an image of which the resolution has been increased four fold! I tested it with this random blurry picture I retrieved from Google/Pinterest.

Do you see how much more detailed (though still blurry) the second image is? Nevertheless, upscaling four times seems about the limit as that is the default factor for both RAISR and Let’s Enhance. I am very curious to see how this super resolution is going to develop in the future, how it will be used to decrease memory or network demands, whether it will be integrated with video platforms like YouTube or Netflix, and which algorithm will ultimately take the crown!