3j9SSKJrJrJr SSKrSSKJrJr SSKJ r J r J r SSK J r JrJr SSKJr S\ 4S jrSS \R&S \R&S \R&S \R&S\\ S\\\\4S\\\\4S\\R&S\\R&\R&44Sjjr"SS5rg))OptionalTupleUnionN)KORNIA_CHECK_LAFKORNIA_CHECK_SHAPE)get_laf_centerget_laf_orientation get_laf_scale) AdalamConfig _no_match adalam_core) dist_matrixreturncP[SSSSSSSSS S [R"S 5S 9 $) zReturn default Adalam Config.dg?Tcpu) area_ratiosearch_expansion ransac_iters min_inliersmin_confidence orientation_difference_thresholdscale_rate_thresholddetected_scale_rate_thresholdrefitforce_seed_mnndevice)r torchr$V/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/feature/adalam/adalam.pyget_adalam_default_configr)!s9 )+ &'||E"  r'desc1desc2lafs1lafs2confighw1hw2dmc[USS/5 [USS/5 [U5 [U5 [5nUcURUS'Oe[5nUR 5HGupXR 5;a+[ SU S[UR 55S35 MCXU 'MI [U5n U R[U5RSS5[U5RSS5UUUU[U5RS5[U5RS5[U5RS5[U5RS5S S 9 upX4$) aYPerform descriptor matching, followed by AdaLAM filtering. See :cite:`AdaLAM2020` for more details. If the distance matrix dm is not provided, :py:func:`torch.cdist` is used. Args: desc1: Batch of descriptors of a shape :math:`(B1, D)`. desc2: Batch of descriptors of a shape :math:`(B2, D)`. lafs1: LAFs of a shape :math:`(1, B1, 2, 3)`. lafs2: LAFs of a shape :math:`(1, B2, 2, 3)`. config: dict with AdaLAM config dm: torch.Tensor containing the distances from each descriptor in desc1 to each descriptor in desc2, shape of :math:`(B1, B2)`. hw1: Height/width of image. hw2: Height/width of image. Return: - Descriptor distance of matching descriptors, shape of :math:`(B3, 1)`. - Long torch.Tensor indexes of matching descriptors in desc1 and desc2. Shape: :math:`(B3, 2)`, where 0 <= B3 <= B1. BDIMr$zFWARNING: custom configuration contains a key which is not recognized (z). Known configurations are .T) return_dist)rrr)r$itemskeysprintlist AdalamFiltermatch_and_filterrreshaper r )r*r+r,r-r.r/r0r1config_keyval adalam_objectidxsqualitys r( match_adalamrF2s`DusEl+usEl+UU')G ~!LL+- HC,,.(\]`\ab004W\\^0D/EQHCL'!)M!22u%%b!,u%%b!,    E"**2.E"**2.e$$R(e$$R(3 MD =r'c<\rSrSrSrSS\\SS4SjjrSS\RS\RS \RS \RS \\RS \\ \ \ 4S \\ \ \ 4S\\RS\\RS\\RS\\RS\ S\ \ \R\R4\R44SjjrSS\RS\RS\RS\RS \\ \ \ 4S \\ \ \ 4S\\RS\\RS\\RS\\RS\ S\ \ \R\R4\R44SjjrSrg)r=wa Implement the AdaLAM (Adaptive Locally-Affine Matching) filter for outlier rejection. This class wraps the AdaLAM algorithm to filter feature matches based on local affine consistency. Args: custom_config: Optional configuration object for AdaLAM parameters. N custom_configrc6UbXlg[5Ulg)aWrap the method AdaLAM for outlier filtering. init args: custom_config: dictionary overriding the default configuration. Missing parameters are kept as default. See documentation of DEFAULT_CONFIG for specific explanations on the accepted parameters. N)r.r))selfrIs r(__init__AdalamFilter.__init__s  $'K35DKr'k1k2putative_matchesscoresmnnim1shapeim2shapeo1o2s1s2r8c [R"5 [UUUUUUUUU U U URU S9 sSSS5 $!,(df  g=f)a Call the core functionality of AdaLAM, i.e. just outlier filtering. No sanity check is performed on the inputs. Args: k1: keypoint locations in the source image, in pixel coordinates. Expected a float32 torch.Tensor with shape (num_keypoints_in_source_image, 2). k2: keypoint locations in the destination image, in pixel coordinates. Expected a float32 torch.Tensor with shape (num_keypoints_in_destination_image, 2). putative_matches: Initial set of putative matches to be filtered. The current implementation assumes that these are unfiltered nearest neighbor matches, so it requires this to be a list of indices a_i such that the source keypoint i is associated to the destination keypoint a_i. For now to use AdaLAM on different inputs a workaround on the input format is required. Expected a long torch.Tensor with shape (num_keypoints_in_source_image,). scores: Confidence scores on the putative_matches. Usually holds Lowe's ratio scores. mnn: A mask indicating which putative matches are also mutual nearest neighbors. See documentation on 'force_seed_mnn' in the DEFAULT_CONFIG. If None, it disables the mutual nearest neighbor filtering on seed point selection. Expected a bool torch.Tensor with shape (num_keypoints_in_source_image,) im1shape: Shape of the source image. If None, it is inferred from keypoints max and min, at the cost of wasted runtime. So please provide it. Expected a tuple with (width, height) or (height, width) of source image im2shape: Shape of the destination image. If None, it is inferred from keypoints max and min, at the cost of wasted runtime. So please provide it. Expected a tuple with (width, height) or (height, width) of destination image o1: keypoint orientations in degrees. They can be None if 'orientation_difference_threshold' in config is set to None. See documentation on 'orientation_difference_threshold' in the DEFAULT_CONFIG. Expected a float32 torch.Tensor with shape (num_keypoints_in_source/destination_image,) o2: same as o1 but for destination. s1: keypoint scales. They can be None if 'scale_rate_threshold' in config is set to None. See documentation on 'scale_rate_threshold' in the DEFAULT_CONFIG. Expected a float32 torch.Tensor with shape (num_keypoints_in_source/destination_image,) s2: same as s1 but for destination. return_dist: if True, inverse confidence value is also outputted. Returns: Filtered putative matches. A long torch.Tensor with shape (num_filtered_matches, 2) with indices of corresponding keypoints in k1 and k2. ) fnn12scores1rRrSrTrUrVrWrXr.r8N)r%no_gradrr.) rKrNrOrPrQrRrSrTrUrVrWrXr8s r(filter_matchesAdalamFilter.filter_matchessKp]]_&!!{{'__s ? A d1d2c U bU cURSb [S5eUbUcURSb [S5e[R"XRS[RS9n [R"X RS[RS9n [R"X0RS[RS9n[R"X@RS[RS9nUba[R"XpRS[RS9n[R"XRS[RS9nOXxnnU ba[R"XRS[RS9n[R"XRS[RS9nOXnn[ U5S::d[ U5S::a[ U5unnU (aUU4$U$[XS S 9n[R"US SS S 9unnUSS2S 4nUSS2S 4USS2S4RS5- nURS(aN[R"US S9unnUU[R"U RS URSS9:HnOSnURXUUUXVUUUUU 5 $)aMatch and filter with AdaLAM. This function: - performs some elementary sanity check on the inputs; - wraps input arrays into torch tensors and loads to GPU if necessary; - extracts nearest neighbors; - finds mutual nearest neighbors if required; - finally calls AdaLAM filtering. Args: k1: keypoint locations in the source image, in pixel coordinates. Expected an array with shape (num_keypoints_in_source_image, 2). k2: keypoint locations in the destination image, in pixel coordinates. Expected an array with shape (num_keypoints_in_destination_image, 2). d1: descriptors in the source image. Expected an array with shape (num_keypoints_in_source_image, descriptor_size). d2: descriptors in the destination image. Expected an array with shape (num_keypoints_in_destination_image, descriptor_size). im1shape: Shape of the source image. If None, it is inferred from keypoints max and min, at the cost of wasted runtime. So please provide it. Expected a tuple with (width, height) or (height, width) of source image im2shape: Shape of the destination image. If None, it is inferred from keypoints max and min, at the cost of wasted runtime. So please provide it. Expected a tuple with (width, height) or (height, width) of destination image o1: keypoint orientations in degrees. They can be None if 'orientation_difference_threshold' in config is set to None. See documentation on 'orientation_difference_threshold' in the DEFAULT_CONFIG. Expected an array with shape (num_keypoints_in_source/destination_image,) o2: Same as o1 for destination. s1: keypoint scales. They can be None if 'scale_rate_threshold' in config is set to None. See documentation on 'scale_rate_threshold' in the DEFAULT_CONFIG. Expected an array with shape (num_keypoints_in_source/destination_image,) s2: Same as s1 for destination. return_dist: if True, inverse confidence value is also outputted. Returns: Filtered putative matches. A long torch.Tensor with shape (num_filtered_matches, 2) with indices of corresponding keypoints in k1 and k2. Nr zCurrent configuration considers keypoint scales for filtering, but scales have not been provided. Please either provide scales or set 'scale_rate_threshold' to None to disable scale filteringrzCurrent configuration considers keypoint orientations for filtering, but orientations have not been provided. Please either provide orientations or set 'orientation_difference_threshold' to None to disable orientations filteringr$)r$dtyper F) is_normalizedr7)kdimlargestrgMbP?r#)re)r$)r.AttributeErrorr% as_tensorfloat32lenr rtopk clamp_min_minarangeshaper])rKrNrOr_r`rSrTrUrVrWrXr8_k1_k2_d1_d2_o1_o2_s1_s2rDdistsdistmatdd12nn12rPrQ_dd21nn21rRs r(r>AdalamFilter.match_and_filterskn :{{12>$t :{{=>J$MoobX)>emmToobX)>emmToobX)>emmToobX)>emmT >//"[[-B%--XC//"[[-B%--XCC >//"[[-B%--XC//"[[-B%--XCC HMs3x1}#C.KD%U{"Kce<ZZ1!UC d1:add1a4j33D99 ;;' ())G3KE4'(ELL1dkkZbNc,ddCC"" &XcSVX[]h  r')r.)N)NNNNNNNF)NNNNNNF)__name__ __module__ __qualname____firstlineno____doc__rr rLr%Tensorrintboolrr]r>__static_attributes__r&r'r(r=r=wsW 6h|&< 6 6$'+.2.2%)%)%)%)!G LLG LLG ,, G  G ell # G5c?+G5c?+G U\\ "G U\\ "G U\\ "G U\\ "GG uU\\5<</0%,,> ?G^/3.2%)%)%)%)!f LLf  LLf  LL f LL f 5c?+ f 5c?+f  U\\ "f  U\\ "f  U\\ "f  U\\ "f f  uU\\5<</0%,,> ?f f r'r=)NNNN)typingrrrr%kornia.core.checkrrkornia.feature.lafrr r corer r rutilsrr)rrrFr=r&r'r(rs,*) BQQ66<,&*%)%)!%B <<B <<B <<B << B \ " B %S/ " B %S/ "B B 5<< %&BJE E r'