Giters

Brummi / derender3d

CVPR 2022 - derender3d: A method for de-rendering a 3D object from a single image into shape, material, and lighting, that is trained in a weakly-supervised fashion relying only on rough shape estimates.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

reproduce Table2

howardchina opened this issue · comments

commented

Hi, thanks for the reproducibility of your code.

A little question about the result of co3d and eval_cosy.py.
I got result as follow:

  35.5Hz       Normal_l1: 0.96366      Normal_mse: 0.17515     Normal_dot: 0.26274     Normal_deviation: 37.98527      Albedo_sie: 0.07594     Albedo_l1: 0.85689      Albedo_ssim: 0.76152    Spec_l1: 0.12306        Spec_mse: 0.07565       Spec_sie: 0.04684

from which Spec_l1: 0.12306 Spec_mse: 0.07565 are different from reported results in Table 2.

commented

Hi, I found I didn't add neural refinement during training.
Can you also provide a co3d_nr.yml for training?