YouTube is testing a brand new resource that allows creators to digitally manipulate their surroundings.

Users can YouTube's new 'Mobile Real-time Video Segmentation' to alter their backgrounds on-screen using new technology.

The feature utilises AI and machine learning to find and replace the background in videos in the same way a green screen does. 

Facial segmentation

The feature is currently only available on mobile intended to work as a feature for 'YouTube stories' - the platform's Snapchat-esque feature.

"To provide high quality data for our machine learning pipeline, we annotated tens of thousands of images that captured a wide spectrum of foreground poses and background settings," YouTube stated in a blog post.

"Annotations consisted of pixel-accurate locations of foreground elements such as hair, glasses, neck, skin, lips, etc. and a general background label achieving a cross-validation result of 98% Intersection-Over-Union (IOU) of human annotator quality." 

This technology is designed to be an easier alternative to using a green screen and chroma keying to change the background of a video. However, the feature is mobile exclusive and may not be of use to creators outside of YouTube Stories just yet.

"Our immediate goal is to use the limited rollout in YouTube stories to test our technology on this first set of effects," YouTube added.

"As we improve and expand our segmentation technology to more labels, we plan to integrate it into Google's broader augmented reality services."