(Image: © Future)
Facebook has a new feature that uses machine learning to turn any ordinary photo into a 3D image that can be viewed from different perspectives if you tilt or rotate your phone, or scroll past.
3D photos have been around for a while on Facebook, but until now it's only been possible to post one if you had a phone with a dual camera, which could capture two images and generate a depth map.
The new tool uses machine learning to extrapolate the three-dimensional shape of objects in your image, and uses that to generate a convincing 3D effect. It can even be used on decades-old images, and it works on any mid-range phone running Android or iOS.
(Image credit: Facebook)Make a Facebook 3D photo
- Launch the Facebook app and tap ‘What’s on your mind’.
- Scroll down and tap ‘3D photo’.
- Select a photo, then wait for it to be processed.
- Preview the 3D effect by moving your phone.
- Add text and any other content to your post, then tap ‘Post’.
Tips for better results
The effect is quite convincing, but the app can't create new data that isn't already in the image, so it will extrapolate what the area behind the picture's subject will look like based on nearby pixels. This will sometimes result in a background that looks a little blurry, so it's best to avoid intricately patterned backdrops.
Facebook says the tool works best if you avoid images with narrow objects in the foreground, or with lots of reflections. It's also a good idea to pick images with objects at various depths for the best effect.
Facebook is currently working to make 3D photos created this way even more convincing, so we look forward to seeing an even more impressive version in the future.