Training data + augmentation process for the 3D model LVD_voxels_SMPL

[DavidBoja]

Hi

thank you for your great work!

I wanted to ask what data did you use to train the 3D version of the code LVD_voxels_SMPL with the IF-Net backbone?

[DavidBoja]

Could you also let me know about the augmentation that is done in 3d? The steps from the supplementary indicate that for each scan you:

1. select a random walking or running pose from a set of poses (which set?)
2. pose the 3D scan by assigning skinning weights of each vertex to those of the closest SMPL point
3. manually remove those that get distorted too much
4. change the first PCA component to augment the shape (how exactly do you do this for the scan? - you shape the SMPL model and then apply the same linear displacements to the scan vertices by using the closest SMPL point displacements?)

and repeat the process 6 times for each scan.

Did I get it right? Is there something else you do?