search

GhiXu / Geo-Neus

Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022)
MIT License
297 stars 18 forks source link

Question on Sampling Strategy #2

Closed anuveshkumar closed 2 years ago

anuveshkumar commented 2 years ago

Hi, I have a doubt related to the sampling strategy used in Photometric and RGB Loss

image

Photometric losses require patches to calculate the NCC.

Are you obtaining the patches by rendering only patches... and using the rendered values for calculating both NCC and RGB loss ?

OR

Are you rendering random pixels (which you use for RGB loss) and then take patches only around those pixels which intersect the object, and the RGB values of the patch comes from the reference image (and not by rendering the remaining pixels) ?

GhiXu commented 2 years ago

Hi, @anuveshkumar, we use the later strategy to compute RGB loss and NCC scores.

anuveshkumar commented 2 years ago

Thank You. That answers my question.