In all probability, there will be no true depth sensing capability in SE, thus developer would not be able to access the api.
The portrait mode is likely to be implemented with monocular depth estimation using deep learning.
The portrait mode is likely to be implemented with monocular depth estimation using deep learning.
Also in the article "We’re happy that this depth data — both the human matte and the newfangled machine-learned depth map — was exposed to us developers, though."