a ždXć@sZddlmZddlZd ejejeejdœdd„Zd ejejejeejejdœdd „ZdS) é)ŚOptionalNF)ŚtauxŚtauyŚreturn_inverseŚreturnc Cs°|j|jkr&td|j›d|j›dƒ‚| ”}| d”}| d”}t |”}t |”}t |”}t |”}t |”}t |”} t  | ||||||| |g d” ddd”} t  ||| || ||||g d” ddd”} | | } |rLd| d} t  | || d| || | d | ||| g d” ddd”}|   dd ”|}|d krHt  |”}|St  | d|| d || d| d  ||| g d” ddd”}||   dd ”}|d kr¬t  |”}|S) aŚEstimate the tilt projection matrix or the inverse tilt projection matrix. Args: taux: Rotation angle in radians around the :math:`x`-axis with shape :math:`(*, 1)`. tauy: Rotation angle in radians around the :math:`y`-axis with shape :math:`(*, 1)`. return_inverse: False to obtain the the tilt projection matrix. True for the inverse matrix. Returns: torch.Tensor: Inverse tilt projection matrix with shape :math:`(*, 3, 3)`. zShape of taux z and tauy z do not match.é’’’’éé).ér ).rr ).r r éž’’’r) ŚshapeŚ ValueErrorŚdimZreshapeŚtorchŚcosŚsinZ zeros_likeŚ ones_likeŚstackŚ transposeZsqueeze)rrrŚndimZcTxZsTxZcTyZsTyZzeroZoneZRxZRyŚRZinvR22ZinvPzZinv_tiltZPzŚtilt©rśl/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/geometry/calibration/distort.pyŚtilt_projectionsD         ** &’ž  *’ž  r)ŚpointsŚKŚdistŚnew_KrcCs¦| ”dkr,|jddkr,td|j›dƒ‚|jdd…dkrPtd|j›dƒ‚|dur^|}n$|jdd…dkr‚td |j›dƒ‚|jdd vr¤td |jd›ƒ‚|jdd krŠtjj |d d |jdg”}|dd d…df}|ddd…df}|dd d…d f}|ddd…df}|d||}|d||} ||| | } d|dd d…f| |ddd…f| | |ddd…f| dd|ddd…f| |ddd…f| | |ddd…f| d} || d|ddd…f|| |ddd…f| d|||ddd…f| |ddd…f| | } | | |ddd…f| d| | d|ddd…f|| |ddd…f| |ddd…f| | } t |dd k”sąt |dd k”r6t|d|dƒ}t  | | t  | ”gd”|  dd”}|d|d} |d|d} |dd d…df}|ddd…df}|dd d…d f}|ddd…df}|| |}|| |} t  || gd”S)a}Distortion of a set of 2D points based on the lens distortion model. Radial :math:`(k_1, k_2, k_3, k_4, k_4, k_6)`, tangential :math:`(p_1, p_2)`, thin prism :math:`(s_1, s_2, s_3, s_4)`, and tilt :math:`(\tau_x, \tau_y)` distortion models are considered in this function. Args: points: Input image points with shape :math:`(*, N, 2)`. K: Intrinsic camera matrix with shape :math:`(*, 3, 3)`. dist: Distortion coefficients :math:`(k_1,k_2,p_1,p_2[,k_3[,k_4,k_5,k_6[,s_1,s_2,s_3,s_4[,\tau_x,\tau_y]]]])`. This is a vector with 4, 5, 8, 12 or 14 elements with shape :math:`(*, n)`. new_K: Intrinsic camera matrix of the distorted image. By default, it is the same as K but you may additionally scale and shift the result by using a different matrix. Shape: :math:`(*, 3, 3)`. Default: None. Returns: Undistorted 2D points with shape :math:`(*, N, 2)`. Example: >>> points = torch.rand(1, 1, 2) >>> K = torch.eye(3)[None] >>> dist_coeff = torch.rand(1, 4) >>> points_dist = distort_points(points, K, dist_coeff) r rzpoints shape is invalid. Got Ś.r N)rrzK matrix shape is invalid. Got z#new_K matrix shape is invalid. Got )éééé éz/Invalid number of distortion coefficients. Got r$r.r ).r).r r r!réér"é é é r#).r#).é ).r ) rr r rŚnnZ functionalŚpadŚanyrrrr)rrrrZnew_cxZnew_cyZnew_fxZnew_fyŚxŚyZr2Zrad_polyZxdZydrZ points_untiltZcxŚcyZfxZfyrrrŚdistort_points;slFF’’žżü’’žżü’ ($  r1)F)N)ŚtypingrrZTensorŚboolrr1rrrrŚs 5’ž