Facebook’s 3D photos are a real attention-grabber, changing perspective as you angle your phone, tap them or scroll past, and while previously you needed a phone with a few cameras to take them yourself, now you can make them even if you only have a basic phone with a single camera.
To give it a try right now, tap ‘What’s on your mind’ and scroll through the list of ‘Add to your post’ options until you find ‘3D photo’. Facebook advises trying not to include long, thin objects in the foreground, and avoiding reflective surfaces. Allow a few minutes for the tool to load, then select your photo and let it do the work.
However, that’s all changed thanks to developers at Facebook Artificial Intelligence, who have created a system that uses machine learning to infer the 3D shape of an object from a 2D photo, making 3D images possible using a basic single-camera phone.
The neural network was trained using a large set of public 3D photos, enabling it to estimate depth with surprising accuracy. It doesn’t have to be a new photo, either; you can also use the tool to transform a picture taken decades ago, bringing old memories back to life.
You don’t need a particularly powerful phone to use the feature – Facebook recommends “an iPhone 7 or higher, or any recent midrange or better Android device.”
Facebook is now working on making the results even more authentic, and is even planning to extend the feature to videos. It’s not just for grabbing attention on friends’ timelines, though; the system has a lot of potential uses in the real world.
“[…] This work will help us better understand the content of 2D images more generally,” the team explained. “Improved understanding of 3D scenes could also help robots navigate and interact with the physical world.
“We hope that by sharing details about our 3D Photos system, we will help the AI community make progress in these areas and create new experiences that leverage advanced 3D understanding.”