Bug in CSPN update step?

[FrederikWarburg]

Hi

As I understand, eq. 6 in arxiv paper should correspond to line:

CSPN/cspn_pytorch/models/cspn.py

Line 81 in b3e487b

result_depth = (1 - sparse_mask) * result_depth + sparse_mask * raw_depth_input

However, raw_depth_input = blur_depth which is the predicted depth by the network. I wondering if

            if sparse_depth is not None:
                result_depth = (
                    1 - sparse_mask
                ) * result_depth + sparse_mask * raw_depth_input

should be

            if sparse_depth is not None:
                result_depth = (
                    1 - sparse_mask
                ) * result_depth + sparse_mask * sparse_depth

such that you keep the depth at the points where you have depth?