


Center: (0.25, 0.25, -0.00) Side lengths: (2.01, 1.50, 1.50)


To make emission view-dependent, we concatenated the harmonic embedding of ray direction to position features, then pass into colour head. Density is kept position dependent only.
| baseline (position only) | view-dependent |
|---|---|
![]() |
![]() |
The view-dependent model places sharper specular highlights on the shiny spheres, but with few training views the model can overfit on those views instead of memorizing a consistent geometry. By keeping density posistion dependent only, geometry stays view-consistent and only emission varies.

Learning rates: means 0.001, scales 0.005, colours 0.005, opacities 0.05
1000 iterations
PSNR: 30.12, SSIM: 0.946

Degree-3 real spherical harmonics evaluated per gaussian along the camera-to-gaussian direction (vectorized over all N gaussians).
Without SH v.s. with SH:

Side-by-side comparisons, left = DC only, right = full SH:

Front view: the full-SH render recovers the gold damask pattern, while the DC-only render averages view-dependent highlights away.

Top view: The full-SH render shows deeper contrast in colors and patterns, with brighter highlights on the gold trim.

Underside view: This view is showing only diffuse and non-shiny surface, so the higher-order SH terms have only small contribution, and the two renderngs look similar.
Baseline — Q6 setup with init_type="random":
PSNR: 19.94, SSIM: 0.702

Improved:
PSNR: 20.79, SSIM: 0.770

Modifications: