Thanks for tuning in to Google I/O. View all sessions on demandWatch on demand

tfg.rendering.camera.perspective.matrix_from_intrinsics

Builds calibration matrix from intrinsic parameters.

tfg.rendering.camera.perspective.matrix_from_intrinsics(
    focal: type_alias.TensorLike,
    principal_point: type_alias.TensorLike,
    skew: type_alias.TensorLike = (0.0,),
    name: str = 'perspective_matrix_from_intrinsics'
) -> tf.Tensor

Builds the camera calibration matrix as

\[ \mathbf{C} = \begin{bmatrix} f_x & sc & c_x \\ 0 & f_y & c_y \\ 0 & 0 & 1 \\ \end{bmatrix} \]

from the focal length \((f_x, f_y)\) and the principal point \((c_x, c_y)\).

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

focal A tensor of shape [A1, ..., An, 2], where the last dimension represents a camera focal length.
principal_point A tensor of shape [A1, ..., An, 2], where the last dimension represents a camera principal point.
skew A tensor of shape [A1, ..., An, 1], where the last dimension represents a skew coefficient.
name A name for this op that defaults to "perspective_matrix_from_intrinsics".

A tensor of shape [A1, ..., An, 3, 3], where the last two dimensions represent a camera calibration matrix.

ValueError If the shape of focal, or principal_point is not supported.