Closed SYSUykLin closed 4 months ago
The input mesh can be coarse (low-polygon), and not fully present the shape details.
Therefore, the sdf feature is needed to present the detailed shape information with the neural decoder and volume rendering techniques.
Close inactive issue but feel free to reopen it if you still have problems.
Each vertex contains a sdf feature and texture feature. But the shape of the objects can be represented by mesh, why do we need the sdf feature?
Thx