tfg.rendering.camera.orthographic.ray

Computes the 3d ray for a 2d point (the z component of the ray is 1).

tfg.rendering.camera.orthographic.ray(
    point_2d: type_alias.TensorLike, name: str = 'orthographic_ray'
) -> tf.Tensor

Computes the 3d ray \((r_x, r_y, 1)\) for a 2d point \((x', y')\) on the image plane. For an orthographic camera the rays are constant over the image plane with

\[ \begin{matrix} r_x = 0, & r_y = 0, & z = 1. \end{matrix} \]

Note: In the following, A1 to An are optional batch dimensions.

Args
point_2d	A tensor of shape [A1, ..., An, 2], where the last dimension represents a 2d point.
name	A name for this op that defaults to "orthographic_ray".

Returns
A tensor of shape [A1, ..., An, 3], where the last dimension represents a 3d ray.

Raises
ValueError	If the shape of point_2d is not supported.