V-Sense / DeepNormals

Code and Dataset from Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

zhansuen_vec

JuHyung-Son opened this issue · comments

Hi,

I'm wondering why did you thining the input sketch.
Is there any reason that data should have thick line?

Artists have different drawing styles and the line thickness can vary. For inference from real-drawing (outside our database) we use the line thinning algorithm.

For training with our dataset this can indeed be disabled.