Apple’s Vision Pro will use machine learning to turn you into a Digital Avatar while you’re FaceTiming. The tech giant said it uses “advanced machine learning”.
- Apple’s Vision Pro headset will let users create a digital avatar so they can have more realistic video chats while their face is partially covered.
An Apple executive called videoconferencing one of the “most difficult challenges” the team faced.
The tech giant said it uses “advanced machine learning” to represent a user’s face and hand movements realistically during FaceTime chats. Users have to scan their faces with the headset’s front-facing cameras to create 3D, hyper-realistic digital avatars.
Apple demoed the feature in an introductory video, saying the system would allow people to see a user’s “eyes, hands, and true expressions” during video chats.
Apple launched the headset, which is the company’s first major product in eight years, at its Apple Worldwide Developers Conference on Monday. The headset has been hotly anticipated and was met with largely positive reviews from critics despite its high price tag.
From the example used in the video, the avatars for Apple’s augmented-reality headset appear to be hyper-realistic, a marked difference from some of Meta’s early attempts at virtual-reality avatars. Meta CEO Mark Zuckerberg was widely mocked after scathing memes were shared in response to a selfie of his early metaverse avatar.
Last year, Zuckerberg shared a picture of his avatar in front of the Eiffel Tower on Facebook. This was quickly seized on by social-media users for its basic graphics. The CEO later posted a more advanced version of the avatar on Instagram in an apparent reaction to the criticism.