google / google/ever

Spherical harmonic degree in forward

Open
#4 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
17
Forks
5
PR merge metrics
No merged PRs in 30d

Description

Thank you for making the code publicly available.

I have a question regarding the color computation in the forward pass. If I'm not wrong, the code in [shaders.slang line 71-80](https://github.com/google/ever/blob/fe6811328991ab03edcff4ef0462292e81be5c3f/splinetracers/fast_ellipsoid_splinetracer/slang/shaders.slang#L71-L80) shows that only SH coefficients of degree 0 are used to compute the color of the ellipsoid, while the backward use all the SH coefficients.

    Features feat;

SHFeatures sh_feats = {prim_ind, sh_degree, features};
feat.f0 = get_sh(sh_feats, 0);
float3 rayd = {0, 0, 1};
let color = eval_sh_col0(rayd, feat);
ctrl_pt.t = t;
ctrl_pt.dirac.x = dirac_height;
ctrl_pt.dirac.y = dirac_height * color.x;
ctrl_pt.dirac.z = dirac_height * color.y;
ctrl_pt.dirac.w = dirac_height * color.z;

Did I miss something?
Thanks

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.