NatML has first-class integration with Unity ARFoundation for adding machine learning to augmented reality applications. We do so by providing ML feature implementations for working with AR camera and depth images:
Making Predictions in AR
Making predictions on the AR camera image closely mirrors the steps we've outlined above. The only difference comes in how we create an image feature for prediction. Instead of using the MLImageFeature class, we will instead use the MLARImageFeature class. First, we need to acquire the current XRCpuImage from ARFoundation: