nerfacc.render_transmittance_from_alpha

nerfacc.render_transmittance_from_alpha(alphas, packed_info=None, ray_indices=None, n_rays=None, prefix_trans=None)

Compute transmittance \(T_i\) from alpha \(\alpha_i\).

\[T_i = \prod_{j=1}^{i-1}(1-\alpha_j)\]

This function supports both batched and flattened input tensor. For flattened input tensor, either (packed_info) or (ray_indices and n_rays) should be provided.

Parameters:

• alphas (Tensor) – The opacity values of the samples. Tensor with shape (all_samples,) or (n_rays, n_samples).

• packed_info (Optional[Tensor]) – A tensor of shape (n_rays, 2) that specifies the start and count of each chunk in the flattened samples, with in total n_rays chunks. Useful for flattened input.

• ray_indices (Optional[Tensor]) – Ray indices of the flattened samples. LongTensor with shape (all_samples).

• n_rays (Optional[int]) – Number of rays. Only useful when ray_indices is provided.

• prefix_trans (Optional[Tensor]) – The pre-computed transmittance of the samples. Tensor with shape (all_samples,).

Returns:

The rendering transmittance with the same shape as alphas.

Return type:

Tensor

Examples:

>>> alphas = torch.tensor([0.4, 0.8, 0.1, 0.8, 0.1, 0.0, 0.9], device="cuda")
>>> ray_indices = torch.tensor([0, 0, 0, 1, 1, 2, 2], device="cuda")
>>> transmittance = render_transmittance_from_alpha(alphas, ray_indices=ray_indices)
tensor([1.0, 0.6, 0.12, 1.0, 0.2, 1.0, 1.0])