Zoom via bilinear interpolation

COUPLED NONNEGATIVE MATRIX FACTORIZATION (CNMF) Copyright (c) 2016 Naoto Yokoya Email: yokoya@sal.rcast.u-tokyo.ac.jp Update: 2016/0

COUPLED NONNEGATIVE MATRIX FACTORIZATION (CNMF) Copyright (c) 2016 Naoto Yokoya Email: yokoya@sal.rcast.u-tokyo.ac.jp Update: 2016/0

Spectral distortion img_fake, generated HRMS img_lm, LRMS

Computes zero padding.

Correlation coefficient for (N, C, H, W) image; torch.float32 [0.,1.].

Computes padding tuple.

ERGAS for 2D (H, W) or 3D (H, W, C) image; uint or float [0, 1]. scale = spatial resolution of PAN / spatial resolution of MUL, default 4.

ERGAS for (N, C, H, W) image; torch.float32 [0.,1.]. scale = spatial resolution of PAN / spatial resolution of MUL, default 4.

Estimation of relative spectral response functions (SRFs) via the nonnegative least squares method USAGE R = estR(HS,MS,mask)

compute fir (finite impulse response) filter with window method Hd: desired freqeuncy response (2D) w: window (2D)

compute fir (finite impulse response) filter with window method Hd: desired freqeuncy response (2D) w: window (2D)

compute fir filter with window method Hd: desired freqeuncy response (2D) w: window (2D)

compute fir filter with window method Hd: desired freqeuncy response (2D) w: window (2D)

r"""Utility function that returns a box filter.

r"""Function that returns Gaussian filter matrix coefficients. Args: kernel_size (Tuple[int, int]): filter sizes in the x and y direction

r"""Function that returns Gaussian filter matrix coefficients. Args: kernel_size (int): filter size should be odd. Returns:

Get local weights for generating the artifact map of LDL. It is only called by the `get_refined_artifact_map` function. Args: residu

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the target is real or fake.

lnL = -1/2 * { ln|Var| + ((X - Mu)^T)(Var^-1)(X - Mu) + kln(2*PI) } k = 1 (Independent) Var = logs ** 2

Nonnegative least squares for spectral unmixing This function solves the following optimization min |Y-AX|_F^2 s.t. X>=0

Percent point function (inverse of cdf) for the normal distribution at p USAGE out = ppf(p,mu,sigma) INPUT p :

PSNR metric, img uint8 if 225; uint16 if 2047

Q-index for 2D (H, W) or 3D (H, W, C) image; uint or float [0, 1]

QNR - No reference IQA

QNR - No reference IQA

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are 'none', 'mean' and 'sum'.

SAM for 3D image, shape (H, W, C); uint or float[0, 1]

SCC for 2D (H, W)or 3D (H, W, C) image; uint or float[0, 1]

SSIM for 2D (H, W) or 3D (H, W, C) image; uint8 if 225; uint16 if 2047

r"""Function that measures the Structural Similarity (SSIM) index between each element in the input `x` and target `y`. See :class:`~kornia.l