search

YuliangXiu / ICON

[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
https://icon.is.tue.mpg.de
Other
1.6k stars 219 forks source link

Question of cloth refinement #162

Closed Yuhuoo closed 1 year ago

Yuhuoo commented 1 year ago

Hi, I'm confused about local_affine_model in the cloth refinement. I find that you use the LocalAffine() converting the verts of the refinemesh to the affined verts. The step seems to train a Affinemodel. I know that we need get the loss between P_normal from the mesh and normal of the image to optimizer the verts, but I don't understand why we need introduct the Affinemodel. The procedure of localAffine is meaning getting the Affine Matrix under the Camera coordinate system? I confused about these.

YuliangXiu commented 1 year ago

This is not a learned model, but a differential optimizer for mesh registration. Please refer to the following paper for more information.

Li, Hao, Robert W. Sumner, and Mark Pauly. "Global correspondence optimization for non‐rigid registration of depth scans." Computer graphics forum. Vol. 27. No. 5. Oxford, UK: Blackwell Publishing Ltd, 2008.