half-potato / nmf

Our method takes as input a collection of images (100 in our experiments) with known cameras, and outputs the volumetric density and normals, materials (BRDFs), and far-field illumination (environment map) of the scene.
https://half-potato.gitlab.io/posts/nmf/
MIT License
52 stars 3 forks source link

Question about roughness #18

Closed gkouros closed 7 months ago

gkouros commented 7 months ago

https://github.com/half-potato/nmf/blob/3f97cd3dd81e5a558499cdaa628382122afad087/models/microfacet.py#L360 Shouldn't the key be "r2" instead of "r1"? Is that a bug or is there a reason behind this?

Also, what do r1 and r2 correspond to? They are the output of the roughness MLP but roughness is usually scalar, so what do the two values correspond to?

Thank you in advance!

half-potato commented 7 months ago

Dear George, The reason there are 2 roughness values is because I originally wanted to handle anisotropic materials, but I ended up only handling isotropic ones. As a result, I regressed two, but set both to be the same.

gkouros commented 7 months ago

Ok. Makes sense now. Thanks for the quick response!