Subscribe via RSS Feed Connect on Google Plus Connect on Flickr

RAISR Sharp Images with Machine Learning

Monday, 6 February, 2017

Rapid and Accurate Image Super-Resolution is a bit of a mouthful so we should welcome the acronym: RAISR. What it means is that machine learning is used to sharpen low-resolution images. Google, which provided the headline for this post, claims that RAISR is so fast that the process can run in real-time on a mobile device. Nerds love this kind of thing, but photographers should be pleased as well because RAISR can avoid aliasing artifacts in the final image, even when artifacts exist in the low-resolution original.

RAISR

Note: Google says it will expand RAISR beyond Android over the coming months and in his recent post on the future of phones, Mobile 2.0, Benedict Evans pointed out the role machine learning will play in the coming changes…

“Web 2.0 was followed not by anything one could call 3.0 but rather a basic platform shift, as the iPhone triggered the move from desktop to mobile as the centre of tech. AirPods, Spectacles, watches and Alexa also reflect or perhaps prefigure platform shifts. In some of them, on one hand, one can see the rise of machine learning as a fundamental new enabling technology, and in some, on the other hand, more and more miniaturisation and optimisation of computing. I think one can see quite a lot of hardware building blocks for augmented reality glasses in some of Apple’s latest little devices, and AR does seem like it could be the next multi-touch, while of course machine learning is also part of that, as computer vision and voice recognition.”


Comments are closed.