Why not estimate coarse albedo from coarse brightness (B_u) directly?
howardchina opened this issue · comments
Qi HE commented
If I get the optimised
Then watching Equation 4, why not just represent coarse albedo from
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.
howardchina opened this issue · comments
If I get the optimised
Then watching Equation 4, why not just represent coarse albedo from