Add Me is an AI-based feature for Google's Pixel 9 phones that lets you add missing individuals into group photos. Google has now explained how this "magic" feature was developed.

When Add Me was first introduced in 2024, Google described it as being able to "seamlessly merge two photos into one amazing image. It combines true-to-the-moment photography with the power of AI and augmented reality, so everyone who was there can be in your pictures."

Add Me is the most recent of a number of AI-based features Google has introduced for its photo apps, including Magic Editor, an AI-powered feature designed to improve your photos in situations where the original isn't quite right, such as when the composition is wrong and you'd like to move things around. Or the sky is too gloomy and you'd like some more sunlight. Magic Editor offers an automatic set of options for editing photos by letting the camera user choose them from the phone menu, and see if the change makes things better or worse.

The latest addition, Add Me, is integrated into the camera on Pixel 9 phones, and it offers a way to add people who weren't there in an original shot. If you have a group photo with someone missing, you can then get that person into the same view, tell them where to stand using directions from the Add Me app that show in the viewfinder, take the second photo, and the Add Me app adds the missing person to the original. It's the opposite of those old photos from repressive regimes where people disappeared from group photos as they fell out of favor with the authorities.

The Add Me feature was a collaboration between the Pixel Camera, Creative Camera and Google XR teams. The Google XR team works on Android XR and ARCore which are platforms for building augmented and virtual reality experiences.

To blend an image, Add Me uses augmented reality (AR) to show the second photographer an overlay of the first image so they can accurately frame the new photo to match the composition of the first one.

Add Me stitches together both photos using AI and augmented reality. Google says Add Me uses various machine learning models, which are powered by Pixel's TPU and the Tensor G4 chip to run on device.

Software engineer Adi Zicher of Google's Creative Camera team says:

"If it weren't for the TPU, I don't think we would have been able to converge to a reasonable latency. If they'd had to run these ML models on a GPU or CPU, the feature wouldn't have been able to display the images from the first shot and then later the blended shot quickly enough."

The TPU is a Tensor Processing Unit that's integrated into the Google Tensor system-on-chip (SoC). It is designed to accelerate AI training and inference.

Google Add Me is available on Pixel 9 phones and from the Google Play Store.

More Information

Add Me On Google Store

Related Articles

Google Introduces JPEG Coding Library

Google Transforms Photos With Magic Editor

Google Cast Adds Output Switcher

Google Ditches Stadia

Google Has Software To Make Cameras Worse

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info