The 3D photo feature was launched in 2018, around the same time smartphones had packing launching dual-lens cameras. The feature took photos with various layers of depth, contrasting colours, and solid texture to create the appearance of a three-dimensional image. It was not supposed on devices that have a single, rear-facing camera.
With the new feature, 3D photos will be available to everyone. The 3D feature captures a foreground subject in great detail while artistically blurring the background. The platform then uses extra data in those image files to create an enhanced image in which background appears to be moving.
The new system infers with the 3D structure of any image, whether it is a new shot captured on an Android or iOS device with a standard single camera or an old image which is recently uploaded to a phone.
In an official announcement, Facebook said, “This advance makes 3D photo technology easily accessible for the first time to the many millions of people who use single-lens camera phones or tablets. Anyone with an iPhone 7 or higher, or a recent midrange or better Android device, can now try these options in the Facebook app.”
Users can experience converting decade-old family photos into 3D with this feature. It took great efforts for Facebook to come up with this feature. Facebook had to build an enhanced 3D photos technique by overcoming various technical challenges.
Facebook explains, “To overcome these challenges, we trained a convolutional neural network (CNN) on millions of pairs of public 3D images and their accompanying depth maps, and leveraged a variety of mobile-optimization techniques previously developed by Facebook AI, such as FBNet and ChamNet.”