Explanation of the optimization equation

[JinraeKim]

In this paper,
I cannot guess the meaning of variables in Eq. (1).

I guess E_D is at least the sum of squares of depth errors.
What is v(p, q)? How can we pick p and q from image N for E_N and E_S?
What is T_{obs} in E_D?

Please give me an explanation with an example.

[JinraeKim]

Also, how did you approximate the equation? There is a reference paper but the notations are different and looks not enough to guess the approximation

[jiayily]

1.T_{obs} is the observed pixels, that is pixels with depth data from both the raw sensor and the rendered mesh.
2.p is a neighbor of q in surface normal image.
3.This vector is used to guarantee consistency between surface normal with predicted depth given p and q is in on the same surface.