“Our new segmentation technology allows creators to replace and modify the background, effortlessly increasing videos’ production value without specialized equipment,” the company said. The technique makes use of neural networks, understanding an image at the pixel level, to determine which parts of a scene are foreground to be left alone and which are background to be replaced. No special equipment is needed, and it has the potential to be used for serious videos as well as the more frivolous things masks tend to be used for at the moment.
The feature is debuting as a beta in the YouTube app, but for the instant only for a limited set of content creators. The effect isn’t perfect yet but for now is about beta tests. It looks however like it could have a big impact. “As we improve and expand our segmentation technology to more labels, we plan to integrate it into Google’s broader Augmented Reality services,” they specified. But the company doesn’t mention a specific timeline to achieve development.