+
    åûjÙ  ã                   ó>   € R t ^RIHtHt ^RIHt ^RIHtHt . ROt	R# )ag  Lens distortion of pixel coordinates with OpenCV's Brown-Conrady model, and camera pose from 3D-2D points.

Image points are pixel coordinates ``(u, v)`` = (column, row) with integer pixel centres, and ``K`` is a ``(*, 3, 3)``
pinhole matrix. ``dist`` is OpenCV's coefficient vector
:math:`(k_1, k_2, p_1, p_2[, k_3[, k_4, k_5, k_6[, s_1, s_2, s_3, s_4[, \tau_x, \tau_y]]]])` of 4, 5, 8, 12 or 14
elements: radial, tangential, thin-prism and sensor-tilt terms, as ``cv2.projectPoints`` and
``cv2.undistortPoints`` read it.

Which function to use:

- Add the distortion to ideal pixels: :func:`distort_points`. Remove it from measured pixels:
  :func:`undistort_points`; from a whole image: :func:`undistort_image`.
- The sensor-tilt matrix of the last two coefficients, or its inverse: :func:`tilt_projection`.
- A world-to-camera pose from ``N >= 6`` world points and their pixels: :func:`solve_pnp_dlt`.
- The Kannala-Brandt fisheye model, on normalized points and a flat parameter vector:
  :func:`~kornia.geometry.camera.distort_points_kannala_brandt` and
  :func:`~kornia.geometry.camera.undistort_points_kannala_brandt`.
)Údistort_pointsÚtilt_projection)Úsolve_pnp_dlt)Úundistort_imageÚundistort_pointsN)r   r   r   r   r   )
Ú__doc__Údistortr   r   Úpnpr   Ú	undistortr   r   Ú__all__© ó    Ú`C:\Ai_Coding\apps\studio\ComfyUI\.venv\Lib\site-packages\kornia\geometry\calibration\__init__.pyÚ<module>r      s   ðñ$÷& 5Ý ß 8â
g‚r   