How to understand "To sample the cone, we cannot follow MipNeRF [3] to use the multivariate Gaussian, since the multivariate Gaussian is anisotropic but the pre-filtering in our Tri-Mip encoding is isotropic."

wbhu / Tri-MipRF

Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields, ICCV'23 (Oral, Best Paper Finalist)

https://wbhu.github.io/projects/Tri-MipRF

450 stars 13 forks source link

How to understand "To sample the cone, we cannot follow MipNeRF [3] to use the multivariate Gaussian, since the multivariate Gaussian is anisotropic but the pre-filtering in our Tri-Mip encoding is isotropic." #34

Open Terry10086 opened 7 months ago

Terry10086 commented 7 months ago

Thanks for your impressive work. I am confused about the sentence mentioned in your paper "To sample the cone, we cannot follow MipNeRF [3] to use the multivariate Gaussian, since the multivariate Gaussian is anisotropic but the pre-filtering in our Tri-Mip encoding is isotropic." I mean why does Tri-Mip need an isotropic characteristic? What is isotropic? Does it mean the same color is observed from different views?

Could you please give more explanation?

wbhu commented 6 months ago

'isotropic' means that the mipmap is pre-filtered with a square kernel, which cannot support sample anisotropic areas