tfg.geometry.representation.ray.sample_stratified_1d

Sample points on a ray using stratified sampling.

tfg.geometry.representation.ray.sample_stratified_1d(
    ray_org: TensorLike,
    ray_dir: TensorLike,
    near: Union[float, TensorLike],
    far: Union[float, TensorLike],
    n_samples: int,
    name: str = 'sample_stratified_1d'
) -> Tuple[tf.Tensor, tf.Tensor]

ray_org A tensor of shape [A1, ..., An, 3], where the last dimension represents the 3D position of the ray origin.
ray_dir A tensor of shape [A1, ..., An, 3], where the last dimension represents the 3D direction of the ray.
near The smallest distance from the ray origin that a sample can have; it can be a float or a tensor of shape [A1, ..., An], broadcast compatible.
far The largest distance from the ray origin that a sample can have; it can be a float or a tensor of shape [A1, ..., An], broadcast compatible.
n_samples A number M to sample on the ray.
name A name for this op that defaults to "stratified_sampling".

A tensor of shape [A1, ..., An, M, 3] indicating the M points on the ray and a tensor of shape [A1, ..., An, M] for the Z values on the points.