nerfacc.accumulate_along_rays

nerfacc.accumulate_along_rays(weights, ray_indices, values=None, n_rays=None)

Accumulate volumetric values along the ray.

Note

This function is only differentiable to weights and values.

Parameters:

• weights (Tensor) – Volumetric rendering weights for those samples. Tensor with shape (n_samples,).

• ray_indices (Tensor) – Ray index of each sample. LongTensor with shape (n_samples).

• values (Optional[Tensor]) – The values to be accmulated. Tensor with shape (n_samples, D). If None, the accumulated values are just weights. Default is None.

• n_rays (Optional[int]) – Total number of rays. This will decide the shape of the ouputs. If None, it will be inferred from ray_indices.max() + 1. If specified it should be at least larger than ray_indices.max(). Default is None.

Returns:

Accumulated values with shape (n_rays, D). If values is not given then we return the accumulated weights, in which case D == 1.

Return type:

Tensor

Examples:

# Rendering: accumulate rgbs, opacities, and depths along the rays.
colors = accumulate_along_rays(weights, ray_indices, values=rgbs, n_rays=n_rays)
opacities = accumulate_along_rays(weights, ray_indices, values=None, n_rays=n_rays)
depths = accumulate_along_rays(
    weights,
    ray_indices,
    values=(t_starts + t_ends) / 2.0,
    n_rays=n_rays,
)
# (n_rays, 3), (n_rays, 1), (n_rays, 1)
print(colors.shape, opacities.shape, depths.shape)