The regular vine copula below
$ f\left(x1,x2,x3\right) = f_{3}\left(x_{3}\right)f_{2}\left(x_{2}\right)f_{1}\left(x_{1}\right) \times c_{12}\left(F_{1}\left(x_{1}\right),F_{2}\left(x_{2}\right)\right)c_{23}\left(F_{2}\left(x_{2}\right),F_{3}\left(x_{3}\right)\right) \times c_{13|2}\left(F_{1|2}\left(x_{1}|x_{2}\right),F_{3|2}\left(x_{3}|x_{2}\right)\right) $
has these terms $x_{1}|x_{2}$ and $x_{3}|x_{2}$. Other vine copulas have a similar construction.
When fitting these models with MLE, how are these conditional terms calculated? For this example, would you regress $x_{1}$ and $x_{3}$ on $x_{2}$ and then use the residuals?
