Faceunity upgrades face tracking algorithms with improved AR SDK
Augmented reality specialist Faceunity Technology has released an updated version of its AR SDK. The improved SDK comes with improved algorithms that are better able to track a person’s face and body movements, allowing the AR platform to map special effects to the subject of a video. more transparent way.
In this regard, the Faceunity SDK is able to recognize up to 241 facial landmarks and is particularly sensitive to landmarks around the eyes and mouth. It can also recognize 56 different types of facial expressions and 25 key landmarks on the human body. It also supports gesture recognition, which allows users to interact with the platform and trigger certain effects with basic movements.
Other SDK features include portrait head and hair segmentation and 3D face model reconstruction. These technologies allow Faceunity to track the position of someone’s face and body in real time, and ensure that any effects that overlay that body are accurately mapped with well-defined borders. On that front, Faceunity’s portfolio includes a wide range of beautification and remodeling features, as well as accessories, stickers, image mats, and background segmentation utilities.
Businesses that want a branded look can use the open-source FU Creator to create their own custom filters, stickers, and effects. The AR SDK is compatible with iOS, Android, PC, Mac and Unity platforms, and can be integrated directly into various applications.
It’s worth nothing that privacy advocates have raised concerns about AR technologies in recent years, largely because people who don’t want their footage captured can easily be caught in the background when people use AR cameras in public. Law enforcement and military organizations have also expressed interest in the technology, though Faceunity’s portfolio is geared more toward the public (and social media and gaming use cases in particular).
April 14, 2022 – by Eric Weiss