what is Foundation pose model input?

[sarvaatmak]

What input does foundation pose model takes I am confused, in document on NGC it is given

• Input Types

• RGB image

• Depth image

• 2D bounding box

• CAD model

• Intrinsic matrix

Thus I am under the impression any one from the above list is enough, is it correct?
or do we have to pass all the above parameters.
if possible can anyone please point me towards the document where it is specifically mentioned?

[wenbowen123]

You are right. You can check run_demo.py file for details.

[sarvaatmak]

do you mean that if i pass only rgb as input without depth or any other parameters it will be enough to predict pose?