nerfacc.ray_resampling

nerfacc.ray_resampling(packed_info, t_starts, t_ends, weights, n_samples)

Resample a set of rays based on the CDF of the weights.

Parameters:

• packed_info (Tensor) – Stores information on which samples belong to the same ray. See nerfacc.ray_marching() for details. Tensor with shape (n_rays, 2).

• t_starts (Tensor) – Where the frustum-shape sample starts along a ray. Tensor with shape (n_samples, 1).

• t_ends (Tensor) – Where the frustum-shape sample ends along a ray. Tensor with shape (n_samples, 1).

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

• n_samples (int) – Number of samples per ray to resample.

Returns:

Resampled packed info (n_rays, 2), t_starts (n_samples, 1), and t_ends (n_samples, 1).

Return type:

Tuple[Tensor, Tensor, Tensor]