Registration is open for TensorFlow Dev Summit 2020 Learn more

Extracts intrinsic parameters from a calibration matrix.

Defined in rendering/camera/

Extracts the focal length \((f_x, f_y)\) and the principal point \((c_x, c_y)\) from a camera calibration matrix

$$ \mathbf{C} = \begin{bmatrix} f_x & 0 & c_x \\ 0 & f_y & c_y \\ 0 & 0 & 1 \\ \end{bmatrix}. $$


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


  • matrix: A tensor of shape [A1, ..., An, 3, 3], where the last two dimensions represent a camera calibration matrix.
  • name: A name for this op that defaults to "perspective_intrinsics_from_matrix".


Tuple of two tensors, each one of shape [A1, ..., An, 2]. The first tensor represents the focal length, and the second one the principle point.


  • ValueError: If the shape of matrix is not supported.