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,
    name=None
)

Defined in rendering/camera/orthographic.py.

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

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

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.