@miniapeur Research scientist (in the US). Nothing wrong with postdoc, but after you finish it, the right answer will still be research scientist (in the US).
@ejdeon This is correct; keeping color and sigma in NeRF separated has various benefits, allowing for separate architectures to learn them, or to discretize one and not the other, etc.
@SebAaltonen I'd recommend creating a procedural material, and training a network that maps a photo to the parameters. Like https://t.co/WskN9ncPd8, ignore the slow differentiable / optimization part, just check the neural network initialization part. The result can be tileable and high-res.
@ejdeon Btw. I believe the paper "Microfacet BRDF generator" [Ashikhmin et al 2000] has a Section 5 that described this coupled BRDF in more detail, so should be a more appropriate reference.
Join us tomorrow at 11am PT for
NeuMIP: Multi-Resolution Neural Materials presentation and Q&A.
You can try it for yourself! Real-time WebGL demo: https://t.co/9jew87c6QV
@twominutepapers made an amazing video covering the paper! https://t.co/vKqzRpZf3S
#SIGGRAPH2021
@Xelatihy Not teaching, but you can easily find the rotation axis of a rotation matrix R (itโs the eigenvector). Then you can rotate around same axis with smaller angle.