Header Banner
Next Reality Logo
Next Reality
Augmented & Mixed Reality News, Rumors & Dev Guides
nextreality.mark.png
Apple Snap AR Business Google Instagram | Facebook NFT HoloLens Magic Leap Hands-On Smartphone AR The Future of AR Next Reality 30 AR Glossary ARKit Dev 101 What Is AR? Mixed Reality HoloLens Dev 101 Augmented Reality Hololens How-Tos HoloLens v. Magic Leap v. Meta 2 VR v. AR v. MR

Google Has Trained a Neural Network to Change Your Video Background in Real-Time Video

Mar 5, 2018 07:48 PM
"Google Has Trained a Neural Network to Change Your Video Background in Real-Time Video" cover image

The research team at Google has found yet another way for machine learning to simplify time-intensive tasks, and this one could eventually facilitate Star Wars-like holographic video.

In a recent blog post, Google researchers demonstrated how a neural network is able to separate the subject of a video in the foreground from the background scene in real time.

The research is already paying off, as YouTube will make this video segmentation ability available in stories, its Snapchat-like video format currently in limited beta with select creators. Users will be able to change their video backgrounds without a green screen or other equipment.

"Our immediate goal is to use the limited rollout in YouTube stories to test our technology on this first set of effects," wrote Valentin Bazarevsky and Andrei Tkachenka, software engineers at Google who led the project. "As we improve and expand our segmentation technology to more labels, we plan to integrate it into Google's broader Augmented Reality services."

We've seen this type of visual magic at work recently via Apple's Clips app. However, that implementation requires the iPhone X and its TrueDepth camera.

Google's computer vision approach could make a similar experience available to a much larger audience. In fact, the team designed the convolutional neural network (CNN) that does the heavy lifting to be light enough to perform on mobile phones at high quality. The method is capable of greater than 100 frames per second (FPS) on iPhone 7 and more than 40 FPS on Pixel 2.

Apple and Google have shown how software can help cut corners in facilitating augmented reality experiences as a substitute for depth sensors. But Google is taking that approach a step further with machine learning. With an eventual eye toward its AR services, it might not be long before holographic video chat is a real thing.

Images via Google

The next big software update for iPhone is coming sometime in April and will include a Food section in Apple News+, an easy-to-miss new Ambient Music app, Priority Notifications thanks to Apple Intelligence, and updates to apps like Mail, Photos, Podcasts, and Safari. See what else is coming to your iPhone with the iOS 18.4 update.

Related Articles

Comments

No Comments Exist

Be the first, drop a comment!