TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tfg.rendering.camera.orthographic.unproject

Unprojects a 2d point in 3d.

tfg.rendering.camera.orthographic.unproject(
    point_2d,
    depth,
    name=None
)

Defined in rendering/camera/orthographic.py.

Unprojects a 2d point \((x', y')\) to a 3d point \((x, y, z)\) given its depth \(z\), with

$$ \begin{matrix} x = x', & y = y', & z = z. \end{matrix} $$

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 to unproject.
  • depth: A tensor of shape [A1, ..., An, 1], where the last dimension represents the depth of a 2d point.
  • name: A name for this op that defaults to "orthographic_unproject".

Returns:

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

Raises:

  • ValueError: If the shape of point_2d, depth is not supported.