Home
Apps
Apps News
Google+ Uses Machine Learning to Display High Resolution Images at a Third of the Bandwidth

Google+ Uses Machine Learning to Display High Resolution Images at a Third of the Bandwidth

By Sanket Vijayasarathy | Updated: 12 January 2017 18:23 IST

Click Here to Add Gadgets360 As A Trusted Source

Highlights

The RAISR technique was first shown in November 2016
RAISR uses machine learning to retain original shapes and details
Google has been applying RAISR to more than 1 billion images per week

Artificial intelligence and machine learning to a significant leap in 2016 with Google launching Assistant for its Pixel and Home products. The company in November also showed off a machine learning technique called RAISR that could be used to enhance low-res and blurry images. 2017 will be no less for Google, which looks to improve the technology further. The RAISR technique is now being used in Google+ which will display high resolution photos using only a third of the bandwidth.

Google in a blog post said that its social networking platform, Google+, will now use the new Rapid and Accurate Image Super-Resolution (RAISR) software which, through machine learning, will allow users to see large high-resolution photos while using 75 percent less bandwidth. This will significantly help those who find themselves with spotty Internet connection and high data costs.

Essentially, RAISR uses machine learning to retain original shapes and details more accurately so as to provide clearer images. As an example, a 100KB 1000x1500 pixels image is replaced with a 25KB file having retained the original resolution through RAISR.

Google said that it has been applying RAISR "to more than 1 billion images per week, reducing these (Android) users’ total bandwidth by about a third." The company plans to roll out the the technology more broadly in the coming weeks so users.

Comments

Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.