Maxine Windows AR SDK
NVIDIA Maxine AR SDK offers AI-based, real-time 3D face tracking and modeling, as well as body pose estimation based on a standard web camera feed. Developers can create unique AR effects such as overlaying 3D content on a face, driving 3D characters and virtual interactions in real time. The SDK is powered by NVIDIA graphics processing units (GPUs) with Tensor Cores, and as a result, the algorithm throughput is greatly accelerated, and latency is reduced.
The SDK has the following AI-powered features:- Face tracking, which detects, localizes, and tracks human faces in images or videos by using bounding boxes.
- Face landmark tracking, which predicts and tracks the pixel locations of human facial landmark points using 68 or 126 landmark points. The 68 detected facial landmarks follow the Multi-PIE 68 point mark-ups information in facial point annotations. The 126 landmark points detector can predict more points on the cheeks, the eyes, and on laugh lines. Additionally, it tracks head pose and facial deformation due to head movement and expression in three degrees of freedom in real time.
- Face mesh, which reconstructs and tracks a human face via a 3D mesh, as well as its head pose, from the provided facial landmarks.
- Body Pose estimation, which predicts and tracks 34 key points of the human body, with joint angles, in 2D and 3D. It also supports multi-person tracking.
- Eye contact, which simulates eye contact by estimating and aligning gaze with the camera to enhance engagement in video communication.
- Face Expression Estimation, which estimates face expression (blendshape) coefficients from the provided facial landmarks.
For more detailed information, please refer to the online documentation guides -
NVIDIA AR SDK Programming Guide
NVIDIA AR SDK System Guide
NvCVImage API Guide
PDF versions of these guides are also available at the following locations -
NVIDIA AR SDK Programming Guide
NVIDIA AR SDK System Guide
NvCVImage API Guide