The Face Framing API makes it possible for web apps to ask the operating system to efficiently apply the automatic face framing effect to a camera's video feed. This eliminates the costly need for manual application of the effect through machine learning frameworks such as TensorFlow.js, Mediapipe, or cloud-based solutions, which require processing each video frame individually.
WebKittens
@youennf
Title of the spec
Media Capture and Streams Extensions
URL to the spec
https://w3c.github.io/mediacapture-extensions/#exposing-mediastreamtrack-source-automatic-face-framing-support
URL to the spec's repository
https://w3c.github.io/mediacapture-extensions/
Issue Tracker URL
No response
Explainer URL
https://github.com/riju/faceFraming/blob/main/explainer.md
TAG Design Review URL
No response
Mozilla standards-positions issue URL
URL
WebKit Bugzilla URL
No response
Radar URL
No response
Description
The Face Framing API makes it possible for web apps to ask the operating system to efficiently apply the automatic face framing effect to a camera's video feed. This eliminates the costly need for manual application of the effect through machine learning frameworks such as TensorFlow.js, Mediapipe, or cloud-based solutions, which require processing each video frame individually.
This is similar to the Background Blur API