3j#,SSKJr SSKrSSKJrJr SSKJrJr /SQr SSjr SSjr SSjr SS jr SSS jjrSSS jjrSSS jjrSSS jjr\rg)) annotationsN)KORNIA_CHECK_IS_TENSORKORNIA_CHECK_SHAPE)convert_points_from_homogeneousconvert_points_to_homogeneous) batched_dot_productbatched_squared_normcompose_transformationseuclidean_distanceinverse_transformationpoint_line_distancerelative_transformation squared_normtransform_pointsc[U5 [U5 UR5S;aURSSS:Xd[SUR35eUR5S;aURSSS:Xd[SUR35eUR5UR5:wa-[SUR5SUR535eUS SS 2SS 24nUS SS 2SS 24nUS SS 2S S24nUS SS 2S S24n[R "X#5n[R "X%5U-nUR UR5nXhS SS 2SS 24'XxS SS 2S S24'S US 'U$) a(Compose two homogeneous transformations. .. math:: T_0^{2} = \begin{bmatrix} R_0^1 R_1^{2} & R_0^{1} t_1^{2} + t_0^{1} \ \\mathbf{0} & 1\end{bmatrix} Args: trans_01: tensor with the homogeneous transformation from a reference frame 1 respect to a frame 0. The tensor has must have a shape of :math:`(N, 4, 4)` or :math:`(4, 4)`. trans_12: tensor with the homogeneous transformation from a reference frame 2 respect to a frame 1. The tensor has must have a shape of :math:`(N, 4, 4)` or :math:`(4, 4)`. Returns: the transformation between the two frames with shape :math:`(N, 4, 4)` or :math:`(4, 4)`. Example:: >>> trans_01 = torch.eye(4) # 4x4 >>> trans_12 = torch.eye(4) # 4x4 >>> trans_02 = compose_transformations(trans_01, trans_12) # 4x4 Nrz8Input trans_01 must be a of the shape Nx4x4 or 4x4. Got z8Input trans_12 must be a of the shape Nx4x4 or 4x4. Got %Input number of dims must match. Got  and .r?.rr)rdimshape ValueErrortorchmatmul new_zeros) trans_01trans_12rmat_01rmat_12tvec_01tvec_12rmat_02tvec_02trans_02s P/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/geometry/linalg.pyr r &s08$8$ \\^v %HNN23,?6,IST\TbTbScdee \\^v %HNN23,?6,IST\TbTbScdee||~'@@PPUV^VbVbVdUefggsBQB{#GsBQB{#GsBQB{#GsBQB{#Gll7,Gll7,w6G!!(..1H#S"1"bqb[#S"1"ab[HY Oc[U5 UR5S;aURSSS:Xd[SUR35eUSSS2SS24nUSSS2SS24nUR S S5n[ R "U*U5nURUR5nUSSS2SS24RU5 USSS2SS24RU5 S US 'U$) aPInvert a 4x4 homogeneous transformation. :math:`T_1^{2} = \begin{bmatrix} R_1 & t_1 \\ \mathbf{0} & 1 \end{bmatrix}` The inverse transformation is computed as follows: .. math:: T_2^{1} = (T_1^{2})^{-1} = \begin{bmatrix} R_1^T & -R_1^T t_1 \\ \mathbf{0} & 1\end{bmatrix} Args: trans_12: transformation tensor of shape :math:`(N, 4, 4)` or :math:`(4, 4)`. Returns: tensor with inverted transformations with shape :math:`(N, 4, 4)` or :math:`(4, 4)`. Example: >>> trans_12 = torch.rand(1, 4, 4) # Nx4x4 >>> trans_21 = inverse_transformation(trans_12) # Nx4x4 rrNrz'Input size must be a Nx4x4 or 4x4. Got .rrrr) rrrr transposerr r!copy_)r#r%r'rmat_21tvec_21trans_21s r+r r [s.8$ \\^v %HNN23,?6,IB8>>BRSTTsBQB{#GsBQB!|$GB'GllG8W-G!!(..1H S"1"bqb[( S"1"ac\  )HY Or,c[U5 [U5 UR5S;aURSSS:Xd[SUR35eUR5S;aURSSS:Xd[SUR35eUR5UR5:Xd-[SUR5SUR535eUSSS 2SS 24nUSSS 2S S 24nUSSS 2SS 24nUSSS 2S S 24nUR S S5n[ R "Xd5n[ R "XeU- 5n[ R"U5n XySSS 2SS 24'XSSS 2S S 24'S U S 'U $)a=Compute the relative homogeneous transformation from a reference transformation. :math:`T_1^{0} = \begin{bmatrix} R_1 & t_1 \\ \mathbf{0} & 1 \end{bmatrix}` to destination :math:`T_2^{0} = \begin{bmatrix} R_2 & t_2 \\ \mathbf{0} & 1 \end{bmatrix}`. The relative transformation is computed as follows: .. math:: T_1^{2} = (T_0^{1})^{-1} \cdot T_0^{2} Args: trans_01: reference transformation tensor of shape :math:`(N, 4, 4)` or :math:`(4, 4)`. trans_02: destination transformation tensor of shape :math:`(N, 4, 4)` or :math:`(4, 4)`. Returns: the relative transformation between the transformations with shape :math:`(N, 4, 4)` or :math:`(4, 4)`. Example:: >>> trans_01 = torch.eye(4) # 4x4 >>> trans_02 = torch.eye(4) # 4x4 >>> trans_12 = relative_transformation(trans_01, trans_02) # 4x4 rrNrz/Input must be a of the shape Nx4x4 or 4x4. Got rr.rrr.rr)rrrrr/rr zeros_like) r"r*r$r&r(r)rmat_10r%r'r#s r+rrs28$8$ \\^v %HNN23,?6,IJ8>>JZ[\\ \\^v %HNN23,?6,IJ8>>JZ[\\ <<>X\\^ +@@PPUV^VbVbVdUefggsBQB{#GsBQB!|$GsBQB{#GsBQB!|$GB'Gll7,Gll7g$56G)H#S"1"bqb[$S"1"ac\HY Or,c[U5 [U5 URSURS:Xd8URSS:wa%[SURSUR35eURSURSS-:Xd[SUSU35e[UR5nUR SURSURS5nUR SURSURS5n[ R "U[URSURS-5SS9n[U5nURn[ R"URUR5URSS S55n[U5nURSUS'URSUS'UR U5nURU5$) aApply transformations to a set of points. Args: trans_01: tensor for transformations of shape :math:`(B, D+1, D+1)`. points_1: tensor of points of shape :math:`(B, N, D)`. Returns: a tensor of N-dimensional points. Shape: - Output: :math:`(B, N, D)` Examples: >>> points_1 = torch.rand(2, 4, 3) # BxNx3 >>> trans_01 = torch.eye(4).view(1, 4, 4) # Bx4x4 >>> points_0 = transform_points(trans_01, points_1) # BxNx3 rz=Input batch size must be the same for both tensors or 1. Got rr.z1Last input dimensions must differ by one unit Gotr)repeatsrr)rrrlistreshaperrepeat_interleaveintrdtypebmmtopermuter)r"points_1 shape_inp points_1_h points_dtype points_0_hpoints_0s r+rrs(8$8$ >>! q 1 1hnnQ6G16LKHNNK[[`aiaoao`p q   >>" (.."4q"8 9LXJV[\d[efggX^^$IHNN2$6r8JKHHNN2$6r8JKH&&xX^^A=NRZR`R`abRc=c9djklH.x8J##L:==8(:J:J1aQR:STJ.z:HNN2&IbMNN2&IbM *H ;;| $$r,c[U5 [U5 URSS;a[SUR35eURSS:wa[SUR35eUSUS-nX1SUS-- nX1S- nUR5 USR 5USR 5-R 5nX4U-- $) aBReturn the distance from points to lines. Args: point: (possibly homogeneous) points :math:`(*, N, 2 or 3)`. line: lines coefficients :math:`(a, b, c)` with shape :math:`(*, N, 3)`, where :math:`ax + by + c = 0`. eps: Small constant for safe sqrt. Returns: the computed distance with shape :math:`(*, N)`. r.rz&pts must be a (*, 2 or 3) tensor. Got rz#lines must be a (*, 3) tensor. Got ).r).r8).r)rrrabs_squaresqrt)pointlineeps numerator denom_norms r+r r s5!4  {{2f$A%++OPP zz"~>tzzlKLLV uV},I ff --I fI NNv,%%'$v,*=*=*??EEGJ S( ))r,cb[USS/5 [USS/5 X-RSU5$)z#Return a batched version of .dot().*Nr.)rsum)xykeepdims r+rr s1q3*%q3*% E;;r7 ##r,c[XU5$)z$Return the squared norm of a vector.)r)rUrWs r+r r s qW --r,c[USS/5 [USS/5 X- RS5RSUS9RU5R 5$)a_Compute the Euclidean distance between two set of n-dimensional points. More: https://en.wikipedia.org/wiki/Euclidean_distance Args: x: first set of points of shape :math:`(*, N)`. y: second set of points of shape :math:`(*, N)`. keepdim: whether to keep the dimension after reduction. eps: small value to have numerical stability. rRrSrr.)rrW)rpowrTadd_sqrt_)rUrVrWrNs r+r r sTq3*%q3*% E;;q>  "g  6 ; ;C @ F F HHr,)r" torch.Tensorr#r]returnr])r#r]r^r])r"r]r*r]r^r])r"r]rBr]r^r])g& .>)rLr]rMr]rNfloatr^r])F)rUr]rVr]rWboolr^r])rUr]rWr`r^r])Fgư>) rUr]rVr]rWr`rNr_r^r]) __future__rrkornia.core.checkrrkornia.geometry.conversionsrr__all__r r rrr rr r rr,r+rfsO$# Hf 2j(V.b2%j*B$. I&$ r,