search

River-Zhang / GTA

[NeurIPS 23] Official repository for NeurIPS 2023 paper "Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction"
https://river-zhang.github.io/GTA-projectpage/
91 stars 4 forks source link

get_sampling_geo #17

Open Followmeczx opened 2 months ago

Followmeczx commented 2 months ago

The get_sampling_geo method is used to obtain the geometric sampling points in the code. smplx_verts can be obtained from smplx_param using the compute_smpl_verts method. image Use load_fit_body in comput_smpl_verts to obtain the mesh of smplx. image The first problem is that: in load_fit_body: image in compute_smpl_verts: image load_fit_body returns the smpl_mesh value of a trimesh to smpl_out, but comput_smpl_verts returns only the vertices of smpl_out. Does that mean that the trimesh step for smpl_verts is not necessary? We just return smpl_verts to smpl_out and smpl_out returns it via comput_smpl_verts. The second problem is that: in load_fit_body: image What are the param['scale'] and param['translation'] and scale? How did you get it?Why can't we just use the vertices obtained by smpl_model via the smplx parameter?

River-Zhang commented 2 weeks ago

The parameters 'scale' and 'translation' are derived from the downloaded SMPLX fits and are used to ensure alignment between the fits and the mesh scan. This approach follows the standard routine as implemented in ICON and ECON.