SangHunHan

@bottler I don't know if I understand your intentions properly, If I can optionally give a list of faces that I want to ignore (transparent) when declaring the shader, that...

I'm sorry I made the explanation difficult. Originally what I wanted to do was to give the vertices/faces an alpha value. I am concerned that If I make a new...

Hi! How did you get full 3D map? Just run ```roslaunch lidar_imu_init xxx.launch``` ??

Thank you for your kind reply. It seems that I should use the result of initialization. However, the recommended value for cut_frame_num = 3 ~ 4 is too low. In...

If you don't mind the extracted UV map being random, I recommend this: https://github.com/jpcy/xatlas However, this does not take into account the structure of the 3D human (e.g. head, hands,...

 It seems strange. Even I rendered with 2048 resolution, it only requires 2~3GB RAM memory. Can you check ```trimesh==3.23.5``` version??

1. I use background augmentation to train both phases. If you changed it along the way, this causes previously trained models to fail to produce correct results. 2. This is...

By the way, is the normal detail well reconstructed in non-edge areas? I want to check if the model is fully trained.

If so, remove all models and losses needed for learning the img2normal_face, upper, arm, leg, and shoe models('part_normal' in self.loss_phase), and only learn "img2normal_down" and "ImgNorm_to_Dep". After these two are...

First, the model does not need to determine what the background is, which prevents incorrect depth predictions for the background. In addition, even in cases where it is difficult to...