Skip to main content

Google can upscale images with finer details using machine learning

google raisr upscale supersample01
Preserving details while enlarging images is one of the hardest tasks to achieve for any Photoshop wizard, but Google may have a new, automated technique which utilizes machine learning to make it a reality. The firm’s new Rapid and Accurate Image Super-Resolution (RAISR) system, is capable of upscaling images without aliasing, achieving increased detail, all in real time on mobile devices.


Google freely admits that it isn’t the first to try and tackle this field of image enhancement. The company is aware of traditional super-resolution and upsampling systems, but feels they can often leave ‘enhanced’ images blurry or aliased, and that the techniques are very slow and cumbersome. With its new RAISR system, it has a technique that actively improves the quality of an image while resizing it, and that does so as much as 100 times faster than competitive systems.

Related: Super sampling dramatically boosts HTC Vive visuals

The RAISR system is able to achieve this effect by ‘teaching’ its algorithm what higher quality images look like. The system then learns which filters can take a lower quality image to a higher quality one without losing clarity or detail. It analyses brightness, color, strength, and other factors to find the “edge” of parts of the image, in order to enhance them using appropriate filters.


The system even analyses the type of image file and the compression that was used during its creation, and uses this information to try and reverse engineer the original structure of the image. This should make it possible for RAISR to undo artifacts produced by a number of different image formats, making it much more versatile, as detailed by Google on its blog (via AndroidPolice).

The end result is larger images which do away with pixelation and blurring to deliver a picture that is more detailed than the original. This will enable all sorts of exciting functions — even beyond making CSI like zooming a reality. We could have further improved pinch-zoom features on phones, and images could be captured or sent at lower resolutions, and then super-sampled only when needed to bring them up to par.

Editors' Recommendations

Jon Martindale
Jon Martindale is the Evergreen Coordinator for Computing, overseeing a team of writers addressing all the latest how to…
Why I still use Microsoft’s Office suite instead of Google’s free options
Computer user touching on Microsoft word icon to open the program.

You can find all sorts of comparisons if you search the internet for Microsoft Office versus Google apps. And these side-by-side comparisons are helpful if you’re deciding between the two productivity suites. If it comes to cost, many simply find Google’s free apps like Docs, Sheets, and Slides the obvious choice. 

But if you’re like me and use these types of applications many, many times per day, or even for running a small business, you have to look at more than the price tag.

Read more
You can now augment Google Lens photo searches with text
Google Lens brings visual searches to the phone.

Google is looking to improve its search results by leveraging both the power of photos, along with additional text for context. The new experience is called multisearch, which will be available on phones and tablets as part of Google Lens inside the Google app.

Google says the feature combines visual and word searches together to deliver the best results possible, even when you can't describe exactly what it is that you're trying to search for.

Read more
Use Google Chrome on Mac? You need to update now
A MacBook with Google Chrome loaded.

Google has sent out a necessary update for the Chrome web browser for the Mac to address a major security hole that was discovered on March 23.

The bug, called CVE-2022-1096, was documented in the Common Vulnerabilities and Exposures (CVE) system by Google developer Prudhvi Kumar Bomman, after an anonymous security researcher discovered a hole in Chrome’s V8 JavaScript engine that left it vulnerable to exploits.

Read more