Question about loss and training of refinement network

[Enuvesta]

Hi! I have two qestions about refinement network:

1. According to the paper loss is calculated as L1 norm of difference between GT sading map and predicted shading map. Also, we can get shaded image I as hadamard product between shading free image and shading map I = A (hadamard prod) S. But there is no GT shading map in the dataset. Does it mean that you calculate ground truth S as I / A (elementwise) for training? Where I is the input image and A is corresponding albedo?

2. Refinement network consists of two UNet-like nets. The first net takes I (input image) as an input and produces N (normals), the second one takes N and produces S (shading map). But loss contains only shading map. So, technically, this is one network and I should use one optimizer for training. Am I right?