Skip to main content

Google can upscale images with finer details using machine learning

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.

supersample02
Google

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.

Recommended Videos

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.

supersample03
Google

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.

Jon Martindale
Jon Martindale is a freelance evergreen writer and occasional section coordinator, covering how to guides, best-of lists, and…
How to use Gemini AI to create presentations in Google Slides
a professional woman giving a slideshow presentation

The only thing people enjoy less than sitting through a slideshow presentation is making a slideshow presentation. But with the integration of Gemini AI into Google Slides, that process is about to get a whole lot easier.

In this guide, we'll explore everything you need to seamlessly incorporate Gemini AI into your workflow. Whether you're looking to enhance your design elements, streamline content generation, or simply save yourself some time, Gemini AI offers a suite of features that can transform the way you build your presentations.
How to integrate Gemini into Google Slides
As with using Google Gemini with Google Sheets, Gemini AI is not available for use with Slides at the free tier. You'll need a $20/month subscription to the Google One AI Premium Plan to gain access; otherwise, a work or school account through a Gemini for Google Workspace add-on will work.

Read more
How to use Gemini AI to write anything in Google Docs
A Gemini branding image

Gemini AI, Google's latest language model, is revolutionizing the way we create content within Google Docs, from drafting emails and reports to generating creative writing pieces.

In this guide, we'll walk you through the steps to access and set up Gemini AI in Google Docs, explore its impressive features, and provide practical examples of how to leverage its potential for a wide range of tasks.
How to integrate Gemini into Google Docs
Unfortunately, basic Google Gemini integration with Google's Workspace suite isn't available to free-tier users. You'll need a $20/month subscription to the Google One AI Premium Plan (or a work or school account through a Gemini for Google Workspace add-on) to gain access. Signing up for the personal plan is straightforward.

Read more
ChatGPT can now generate images for free using Dall-E
ChatGPT results on an iPhone.

Since its launch last September, OpenAI's Dall-E 3 image generator has only been available to its Plus, Teams, and Enterprise subscribers. Now, nearly a year later, Dall-E is accessible to the rest of us — just with some stringent restrictions.

https://twitter.com/OpenAI/status/1821644904843636871

Read more