




After training, the box center is (0.25, 0.25, 0.00) and the side lengths are (2.01, 1.50, 1.50).






Trained on the lego scene for 250 epochs at 128x128. The final training MSE was 0.0032.

The viewing direction is encoded with a low frequency embedding and concatenated to the 128 dim feature vector at the input of the color head.


Alpha sets the density inside the object, and beta sets how quickly that density falls to zero across the surface.
Hyperparameters: I kept alpha = 10 and beta = 0.05, and trained for 250 epochs with a learning rate of 5e-4. Beta = 0.05 is still wider than the sample spacing of about 0.03, so the surface band gets sampled.
I compared three runs.
The default init starts the SDF near zero everywhere, which leaves surface fragments in regions no camera sees. Starting from a sphere gives a valid SDF that training only has to carve down, and the stronger eikonal term keeps empty space clean.
Command: implicit_function.geometric_init=True training.eikonal_weight=0.1



| Parameter | Learning rate |
|---|---|
| opacities (pre-activation) | 0.05 |
| scales (log) | 0.005 |
| colours | 0.02 |
| means | 0.0005 |
--gaussians_per_splat 2048)




Left: DC term only (Q5.5). Right: full spherical harmonics (Q7.1).