KAIR/utils/utils_blindsr.py

# -*- coding: utf-8 -*-
import numpy as np
import cv2
import torch

from utils import utils_image as util

import random
from scipy import ndimage
import scipy
import scipy.stats as ss
from scipy.interpolate import interp2d
from scipy.linalg import orth




"""
# --------------------------------------------
# super-resolution
# --------------------------------------------
#
# kai zhang (cskaizhang@gmail.com)
# https://github.com/cszn
# from 2019/03--2021/08
# --------------------------------------------
"""

def modcrop_np(img, sf):
    '''
    args:
        img: numpy image, wxh or wxhxc
        sf: scale factor

    return:
        cropped image
    '''
    w, h = img.shape[:2]
    im = np.copy(img)
    return im[:w - w % sf, :h - h % sf, ...]


"""
# --------------------------------------------
# anisotropic gaussian kernels
# --------------------------------------------
"""
def analytic_kernel(k):
    """calculate the x4 kernel from the x2 kernel (for proof see appendix in paper)"""
    k_size = k.shape[0]
    # calculate the big kernels size
    big_k = np.zeros((3 * k_size - 2, 3 * k_size - 2))
    # loop over the small kernel to fill the big one
    for r in range(k_size):
        for c in range(k_size):
            big_k[2 * r:2 * r + k_size, 2 * c:2 * c + k_size] += k[r, c] * k
    # crop the edges of the big kernel to ignore very small values and increase run time of sr
    crop = k_size // 2
    cropped_big_k = big_k[crop:-crop, crop:-crop]
    # normalize to 1
    return cropped_big_k / cropped_big_k.sum()


def anisotropic_gaussian(ksize=15, theta=np.pi, l1=6, l2=6):
    """ generate an anisotropic gaussian kernel
    args:
        ksize : e.g., 15, kernel size
        theta : [0,  pi], rotation angle range
        l1    : [0.1,50], scaling of eigenvalues
        l2    : [0.1,l1], scaling of eigenvalues
        if l1 = l2, will get an isotropic gaussian kernel.

    returns:
        k     : kernel
    """

    v = np.dot(np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]]), np.array([1., 0.]))
    v = np.array([[v[0], v[1]], [v[1], -v[0]]])
    d = np.array([[l1, 0], [0, l2]])
    sigma = np.dot(np.dot(v, d), np.linalg.inv(v))
    k = gm_blur_kernel(mean=[0, 0], cov=sigma, size=ksize)

    return k


def gm_blur_kernel(mean, cov, size=15):
    center = size / 2.0 + 0.5
    k = np.zeros([size, size])
    for y in range(size):
        for x in range(size):
            cy = y - center + 1
            cx = x - center + 1
            k[y, x] = ss.multivariate_normal.pdf([cx, cy], mean=mean, cov=cov)

    k = k / np.sum(k)
    return k


def shift_pixel(x, sf, upper_left=true):
    """shift pixel for super-resolution with different scale factors
    args:
        x: wxhxc or wxh
        sf: scale factor
        upper_left: shift direction
    """
    h, w = x.shape[:2]
    shift = (sf-1)*0.5
    xv, yv = np.arange(0, w, 1.0), np.arange(0, h, 1.0)
    if upper_left:
        x1 = xv + shift
        y1 = yv + shift
    else:
        x1 = xv - shift
        y1 = yv - shift

    x1 = np.clip(x1, 0, w-1)
    y1 = np.clip(y1, 0, h-1)

    if x.ndim == 2:
        x = interp2d(xv, yv, x)(x1, y1)
    if x.ndim == 3:
        for i in range(x.shape[-1]):
            x[:, :, i] = interp2d(xv, yv, x[:, :, i])(x1, y1)

    return x


def blur(x, k):
    '''
    x: image, nxcxhxw
    k: kernel, nx1xhxw
    '''
    n, c = x.shape[:2]
    p1, p2 = (k.shape[-2]-1)//2, (k.shape[-1]-1)//2
    x = torch.nn.functional.pad(x, pad=(p1, p2, p1, p2), mode='replicate')
    k = k.repeat(1,c,1,1)
    k = k.view(-1, 1, k.shape[2], k.shape[3])
    x = x.view(1, -1, x.shape[2], x.shape[3])
    x = torch.nn.functional.conv2d(x, k, bias=none, stride=1, padding=0, groups=n*c)
    x = x.view(n, c, x.shape[2], x.shape[3])

    return x



def gen_kernel(k_size=np.array([15, 15]), scale_factor=np.array([4, 4]), min_var=0.6, max_var=10., noise_level=0):
    """"
    # modified version of https://github.com/assafshocher/blindsr_dataset_generator
    # kai zhang
    # min_var = 0.175 * sf  # variance of the gaussian kernel will be sampled between min_var and max_var
    # max_var = 2.5 * sf
    """
    # set random eigen-vals (lambdas) and angle (theta) for cov matrix
    lambda_1 = min_var + np.random.rand() * (max_var - min_var)
    lambda_2 = min_var + np.random.rand() * (max_var - min_var)
    theta = np.random.rand() * np.pi  # random theta
    noise = -noise_level + np.random.rand(*k_size) * noise_level * 2

    # set cov matrix using lambdas and theta
    lambda = np.diag([lambda_1, lambda_2])
    q = np.array([[np.cos(theta), -np.sin(theta)],
                  [np.sin(theta), np.cos(theta)]])
    sigma = q @ lambda @ q.t
    inv_sigma = np.linalg.inv(sigma)[none, none, :, :]

    # set expectation position (shifting kernel for aligned image)
    mu = k_size // 2 - 0.5*(scale_factor - 1) # - 0.5 * (scale_factor - k_size % 2)
    mu = mu[none, none, :, none]

    # create meshgrid for gaussian
    [x,y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
    z = np.stack([x, y], 2)[:, :, :, none]

    # calcualte gaussian for every pixel of the kernel
    zz = z-mu
    zz_t = zz.transpose(0,1,3,2)
    raw_kernel = np.exp(-0.5 * np.squeeze(zz_t @ inv_sigma @ zz)) * (1 + noise)

    # shift the kernel so it will be centered
    #raw_kernel_centered = kernel_shift(raw_kernel, scale_factor)

    # normalize the kernel and return
    #kernel = raw_kernel_centered / np.sum(raw_kernel_centered)
    kernel = raw_kernel / np.sum(raw_kernel)
    return kernel


def fspecial_gaussian(hsize, sigma):
    hsize = [hsize, hsize]
    siz = [(hsize[0]-1.0)/2.0, (hsize[1]-1.0)/2.0]
    std = sigma
    [x, y] = np.meshgrid(np.arange(-siz[1], siz[1]+1), np.arange(-siz[0], siz[0]+1))
    arg = -(x*x + y*y)/(2*std*std)
    h = np.exp(arg)
    h[h < scipy.finfo(float).eps * h.max()] = 0
    sumh = h.sum()
    if sumh != 0:
        h = h/sumh
    return h


def fspecial_laplacian(alpha):
    alpha = max([0, min([alpha,1])])
    h1 = alpha/(alpha+1)
    h2 = (1-alpha)/(alpha+1)
    h = [[h1, h2, h1], [h2, -4/(alpha+1), h2], [h1, h2, h1]]
    h = np.array(h)
    return h


def fspecial(filter_type, *args, **kwargs):
    '''
    python code from:
    https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/aulas/aula_2_-_uniform_filter/matlab_fspecial.py
    '''
    if filter_type == 'gaussian':
        return fspecial_gaussian(*args, **kwargs)
    if filter_type == 'laplacian':
        return fspecial_laplacian(*args, **kwargs)

"""
# --------------------------------------------
# degradation models
# --------------------------------------------
"""


def bicubic_degradation(x, sf=3):
    '''
    args:
        x: hxwxc image, [0, 1]
        sf: down-scale factor

    return:
        bicubicly downsampled lr image
    '''
    x = util.imresize_np(x, scale=1/sf)
    return x


def srmd_degradation(x, k, sf=3):
    ''' blur + bicubic downsampling

    args:
        x: hxwxc image, [0, 1]
        k: hxw, double
        sf: down-scale factor

    return:
        downsampled lr image

    reference:
        @inproceedings{zhang2018learning,
          title={learning a single convolutional super-resolution network for multiple degradations},
          author={zhang, kai and zuo, wangmeng and zhang, lei},
          booktitle={ieee conference on computer vision and pattern recognition},
          pages={3262--3271},
          year={2018}
        }
    '''
    x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap')  # 'nearest' | 'mirror'
    x = bicubic_degradation(x, sf=sf)
    return x


def dpsr_degradation(x, k, sf=3):

    ''' bicubic downsampling + blur

    args:
        x: hxwxc image, [0, 1]
        k: hxw, double
        sf: down-scale factor

    return:
        downsampled lr image

    reference:
        @inproceedings{zhang2019deep,
          title={deep plug-and-play super-resolution for arbitrary blur kernels},
          author={zhang, kai and zuo, wangmeng and zhang, lei},
          booktitle={ieee conference on computer vision and pattern recognition},
          pages={1671--1681},
          year={2019}
        }
    '''
    x = bicubic_degradation(x, sf=sf)
    x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap')
    return x


def classical_degradation(x, k, sf=3):
    ''' blur + downsampling

    args:
        x: hxwxc image, [0, 1]/[0, 255]
        k: hxw, double
        sf: down-scale factor

    return:
        downsampled lr image
    '''
    x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap')
    #x = filters.correlate(x, np.expand_dims(np.flip(k), axis=2))
    st = 0
    return x[st::sf, st::sf, ...]


def add_sharpening(img, weight=0.5, radius=50, threshold=10):
    """usm sharpening. borrowed from real-esrgan
    input image: i; blurry image: b.
    1. k = i + weight * (i - b)
    2. mask = 1 if abs(i - b) > threshold, else: 0
    3. blur mask:
    4. out = mask * k + (1 - mask) * i
    args:
        img (numpy array): input image, hwc, bgr; float32, [0, 1].
        weight (float): sharp weight. default: 1.
        radius (float): kernel size of gaussian blur. default: 50.
        threshold (int):
    """
    if radius % 2 == 0:
        radius += 1
    blur = cv2.gaussianblur(img, (radius, radius), 0)
    residual = img - blur
    mask = np.abs(residual) * 255 > threshold
    mask = mask.astype('float32')
    soft_mask = cv2.gaussianblur(mask, (radius, radius), 0)

    k = img + weight * residual
    k = np.clip(k, 0, 1)
    return soft_mask * k + (1 - soft_mask) * img


def add_blur(img, sf=4):
    wd2 = 4.0 + sf
    wd = 2.0 + 0.2*sf
    if random.random() < 0.5:
        l1 = wd2*random.random()
        l2 = wd2*random.random()
        k = anisotropic_gaussian(ksize=2*random.randint(2,11)+3, theta=random.random()*np.pi, l1=l1, l2=l2)
    else:
        k = fspecial('gaussian', 2*random.randint(2,11)+3, wd*random.random())
    img = ndimage.filters.convolve(img, np.expand_dims(k, axis=2), mode='mirror')

    return img


def add_resize(img, sf=4):
    rnum = np.random.rand()
    if rnum > 0.8:  # up
        sf1 = random.uniform(1, 2)
    elif rnum < 0.7:  # down
        sf1 = random.uniform(0.5/sf, 1)
    else:
        sf1 = 1.0
    img = cv2.resize(img, (int(sf1*img.shape[1]), int(sf1*img.shape[0])), interpolation=random.choice([1, 2, 3]))
    img = np.clip(img, 0.0, 1.0)

    return img


def add_gaussian_noise(img, noise_level1=2, noise_level2=25):
    noise_level = random.randint(noise_level1, noise_level2)
    rnum = np.random.rand()
    if rnum > 0.6:   # add color gaussian noise
        img += np.random.normal(0, noise_level/255.0, img.shape).astype(np.float32)
    elif rnum < 0.4: # add grayscale gaussian noise
        img += np.random.normal(0, noise_level/255.0, (*img.shape[:2], 1)).astype(np.float32)
    else:            # add  noise
        l = noise_level2/255.
        d = np.diag(np.random.rand(3))
        u = orth(np.random.rand(3,3))
        conv = np.dot(np.dot(np.transpose(u), d), u)
        img += np.random.multivariate_normal([0,0,0], np.abs(l**2*conv), img.shape[:2]).astype(np.float32)
    img = np.clip(img, 0.0, 1.0)
    return img


def add_speckle_noise(img, noise_level1=2, noise_level2=25):
    noise_level = random.randint(noise_level1, noise_level2)
    img = np.clip(img, 0.0, 1.0)
    rnum = random.random()
    if rnum > 0.6:
        img += img*np.random.normal(0, noise_level/255.0, img.shape).astype(np.float32)
    elif rnum < 0.4:
        img += img*np.random.normal(0, noise_level/255.0, (*img.shape[:2], 1)).astype(np.float32)
    else:
        l = noise_level2/255.
        d = np.diag(np.random.rand(3))
        u = orth(np.random.rand(3,3))
        conv = np.dot(np.dot(np.transpose(u), d), u)
        img += img*np.random.multivariate_normal([0,0,0], np.abs(l**2*conv), img.shape[:2]).astype(np.float32)
    img = np.clip(img, 0.0, 1.0)
    return img


def add_poisson_noise(img):
    img = np.clip((img * 255.0).round(), 0, 255) / 255.
    vals = 10**(2*random.random()+2.0)  # [2, 4]
    if random.random() < 0.5:
        img = np.random.poisson(img * vals).astype(np.float32) / vals
    else:
        img_gray = np.dot(img[...,:3], [0.299, 0.587, 0.114])
        img_gray = np.clip((img_gray * 255.0).round(), 0, 255) / 255.
        noise_gray = np.random.poisson(img_gray * vals).astype(np.float32) / vals - img_gray
        img += noise_gray[:, :, np.newaxis]
    img = np.clip(img, 0.0, 1.0)
    return img


def add_jpeg_noise(img):
    quality_factor = random.randint(30, 95)
    img = cv2.cvtcolor(util.single2uint(img), cv2.color_rgb2bgr)
    result, encimg = cv2.imencode('.jpg', img, [int(cv2.imwrite_jpeg_quality), quality_factor])
    img = cv2.imdecode(encimg, 1)
    img = cv2.cvtcolor(util.uint2single(img), cv2.color_bgr2rgb)
    return img


def random_crop(lq, hq, sf=4, lq_patchsize=64):
    h, w = lq.shape[:2]
    rnd_h = random.randint(0, h-lq_patchsize)
    rnd_w = random.randint(0, w-lq_patchsize)
    lq = lq[rnd_h:rnd_h + lq_patchsize, rnd_w:rnd_w + lq_patchsize, :]

    rnd_h_h, rnd_w_h = int(rnd_h * sf), int(rnd_w * sf)
    hq = hq[rnd_h_h:rnd_h_h + lq_patchsize*sf, rnd_w_h:rnd_w_h + lq_patchsize*sf, :]
    return lq, hq


def degradation_bsrgan(img, sf=4, lq_patchsize=72, isp_model=none):
    """
    this is the degradation model of bsrgan from the paper
    "designing a practical degradation model for deep blind image super-resolution"
    ----------
    img: hxwxc, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
    sf: scale factor
    isp_model: camera isp model

    returns
    -------
    img: low-quality patch, size: lq_patchsizexlq_patchsizexc, range: [0, 1]
    hq: corresponding high-quality patch, size: (lq_patchsizexsf)x(lq_patchsizexsf)xc, range: [0, 1]
    """
    isp_prob, jpeg_prob, scale2_prob = 0.25, 0.9, 0.25
    sf_ori = sf

    h1, w1 = img.shape[:2]
    img = img.copy()[:w1 - w1 % sf, :h1 - h1 % sf, ...]  # mod crop
    h, w = img.shape[:2]

    if h < lq_patchsize*sf or w < lq_patchsize*sf:
        raise valueerror(f'img size ({h1}x{w1}) is too small!')

    hq = img.copy()

    if sf == 4 and random.random() < scale2_prob:   # downsample1
        if np.random.rand() < 0.5:
            img = cv2.resize(img, (int(1/2*img.shape[1]), int(1/2*img.shape[0])), interpolation=random.choice([1,2,3]))
        else:
            img = util.imresize_np(img, 1/2, true)
        img = np.clip(img, 0.0, 1.0)
        sf = 2

    shuffle_order = random.sample(range(7), 7)
    idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
    if idx1 > idx2:  # keep downsample3 last
        shuffle_order[idx1], shuffle_order[idx2] = shuffle_order[idx2], shuffle_order[idx1]

    for i in shuffle_order:

        if i == 0:
            img = add_blur(img, sf=sf)

        elif i == 1:
            img = add_blur(img, sf=sf)

        elif i == 2:
            a, b = img.shape[1], img.shape[0]
            # downsample2
            if random.random() < 0.75:
                sf1 = random.uniform(1,2*sf)
                img = cv2.resize(img, (int(1/sf1*img.shape[1]), int(1/sf1*img.shape[0])), interpolation=random.choice([1,2,3]))
            else:
                k = fspecial('gaussian', 25, random.uniform(0.1, 0.6*sf))
                k_shifted = shift_pixel(k, sf)
                k_shifted = k_shifted/k_shifted.sum()  # blur with shifted kernel
                img = ndimage.filters.convolve(img, np.expand_dims(k_shifted, axis=2), mode='mirror')
                img = img[0::sf, 0::sf, ...]  # nearest downsampling
            img = np.clip(img, 0.0, 1.0)

        elif i == 3:
            # downsample3
            img = cv2.resize(img, (int(1/sf*a), int(1/sf*b)), interpolation=random.choice([1,2,3]))
            img = np.clip(img, 0.0, 1.0)

        elif i == 4:
            # add gaussian noise
            img = add_gaussian_noise(img, noise_level1=2, noise_level2=25)

        elif i == 5:
            # add jpeg noise
            if random.random() < jpeg_prob:
                img = add_jpeg_noise(img)

        elif i == 6:
            # add processed camera sensor noise
            if random.random() < isp_prob and isp_model is not none:
                with torch.no_grad():
                    img, hq = isp_model.forward(img.copy(), hq)

    # add final jpeg compression noise
    img = add_jpeg_noise(img)

    # random crop
    img, hq = random_crop(img, hq, sf_ori, lq_patchsize)

    return img, hq




def degradation_bsrgan_plus(img, sf=4, shuffle_prob=0.5, use_sharp=false, lq_patchsize=64, isp_model=none):
    """
    this is an extended degradation model by combining
    the degradation models of bsrgan and real-esrgan
    ----------
    img: hxwxc, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
    sf: scale factor
    use_shuffle: the degradation shuffle
    use_sharp: sharpening the img

    returns
    -------
    img: low-quality patch, size: lq_patchsizexlq_patchsizexc, range: [0, 1]
    hq: corresponding high-quality patch, size: (lq_patchsizexsf)x(lq_patchsizexsf)xc, range: [0, 1]
    """

    h1, w1 = img.shape[:2]
    img = img.copy()[:w1 - w1 % sf, :h1 - h1 % sf, ...]  # mod crop
    h, w = img.shape[:2]

    if h < lq_patchsize*sf or w < lq_patchsize*sf:
        raise valueerror(f'img size ({h1}x{w1}) is too small!')

    if use_sharp:
        img = add_sharpening(img)
    hq = img.copy()

    if random.random() < shuffle_prob:
        shuffle_order = random.sample(range(13), 13)
    else:
        shuffle_order = list(range(13))
        # local shuffle for noise, jpeg is always the last one
        shuffle_order[2:6] = random.sample(shuffle_order[2:6], len(range(2, 6)))
        shuffle_order[9:13] = random.sample(shuffle_order[9:13], len(range(9, 13)))

    poisson_prob, speckle_prob, isp_prob = 0.1, 0.1, 0.1

    for i in shuffle_order:
        if i == 0:
            img = add_blur(img, sf=sf)
        elif i == 1:
            img = add_resize(img, sf=sf)
        elif i == 2:
            img = add_gaussian_noise(img, noise_level1=2, noise_level2=25)
        elif i == 3:
            if random.random() < poisson_prob:
                img = add_poisson_noise(img)
        elif i == 4:
            if random.random() < speckle_prob:
                img = add_speckle_noise(img)
        elif i == 5:
            if random.random() < isp_prob and isp_model is not none:
                with torch.no_grad():
                    img, hq = isp_model.forward(img.copy(), hq)
        elif i == 6:
            img = add_jpeg_noise(img)
        elif i == 7:
            img = add_blur(img, sf=sf)
        elif i == 8:
            img = add_resize(img, sf=sf)
        elif i == 9:
            img = add_gaussian_noise(img, noise_level1=2, noise_level2=25)
        elif i == 10:
            if random.random() < poisson_prob:
                img = add_poisson_noise(img)
        elif i == 11:
            if random.random() < speckle_prob:
                img = add_speckle_noise(img)
        elif i == 12:
            if random.random() < isp_prob and isp_model is not none:
                with torch.no_grad():
                    img, hq = isp_model.forward(img.copy(), hq)
        else:
            print('check the shuffle!')

    # resize to desired size
    img = cv2.resize(img, (int(1/sf*hq.shape[1]), int(1/sf*hq.shape[0])), interpolation=random.choice([1, 2, 3]))

    # add final jpeg compression noise
    img = add_jpeg_noise(img)

    # random crop
    img, hq = random_crop(img, hq, sf, lq_patchsize)

    return img, hq



if __name__ == '__main__':
    img = util.imread_uint('utils/test.png', 3)
    img = util.uint2single(img)
    sf = 4

    for i in range(20):
        img_lq, img_hq = degradation_bsrgan(img, sf=sf, lq_patchsize=72)
        print(i)
        lq_nearest =  cv2.resize(util.single2uint(img_lq), (int(sf*img_lq.shape[1]), int(sf*img_lq.shape[0])), interpolation=0)
        img_concat = np.concatenate([lq_nearest, util.single2uint(img_hq)], axis=1)
        util.imsave(img_concat, str(i)+'.png')

#    for i in range(10):
#        img_lq, img_hq = degradation_bsrgan_plus(img, sf=sf, shuffle_prob=0.1, use_sharp=true, lq_patchsize=64)
#        print(i)
#        lq_nearest =  cv2.resize(util.single2uint(img_lq), (int(sf*img_lq.shape[1]), int(sf*img_lq.shape[0])), interpolation=0)
#        img_concat = np.concatenate([lq_nearest, util.single2uint(img_hq)], axis=1)
#        util.imsave(img_concat, str(i)+'.png')

#    run utils/utils_blindsr.py