We'd like to use an object both as a source for a USDZ based on the PhotogrammetrySession and as an ARReferenceObject, so that we can overlay information at the same position on both the real object and the created model.Is there any guidance on how to align these coordinate systems, e.g. by aligning the point clouds from the photogrammetry session and reference object? Or can we make assumptions on the origin of the resulting USDZ from the PhotogrammetrySession?
Creating a model for Object Detection and creating a textured mesh with Object Capture are two different use cases with separate workflows, we do not offer a tool to convert from one to another. That sounds like a great use case though, I encourage you to file a feature request.