MoveNet - Realtime Pose Tracking

Perform realtime human pose tracking with the MoveNet machine learning model. This package requires NatML to run the machine learning model. Features include:

+ Bare Metal Performance. The MoveNet predictor is implemented with NatML, which takes advantage of hardware machine learning accelerators, like CoreML on iOS and macOS, NNAPI on Android, and DirectML on Windows.

+ Extremely Easy to Use. The MoveNet predictor accepts an image (Texture2D, WebCamTexture, NatDevice, and more) and returns a 2D body pose with 17 along with the confidence score (float). As such, it can be used in a one-liner. See more on NatML Hub.

+ Cross Platform. The MoveNet predictor supports Android, iOS, macOS, and Windows alike. As such you can test it in the Editor, and deploy it to the device all in one seamless workflow.

+ Augmented Reality. This predictor is particularly suited for augmented reality applications, where it can enhance gameplay by recognizing objects in the scene.

+ Lightweight Package. This package contains the predictor scripts, whereas the ML model will be downloaded at runtime from NatML Hub and cached onto the device, reducing the app size significantly.

Find other ML models on NatML Hub.

Join the NatML community on Discord.

Check out the NatML documentation.

See more NatML projects on GitHub.

Read the NatML blog.

Discuss NatML on Unity Forums.

Contact us at [email protected].