Upload utils_util_calculate_psnr_ssim.py

utils/utils_util_calculate_psnr_ssim.py

@@ -0,0 +1,346 @@
+import cv2
+import numpy as np
+import torch
+
+
+def calculate_psnr(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
+    """Calculate PSNR (Peak Signal-to-Noise Ratio).
+
+    Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio
+
+    Args:
+        img1 (ndarray): Images with range [0, 255].
+        img2 (ndarray): Images with range [0, 255].
+        crop_border (int): Cropped pixels in each edge of an image. These
+            pixels are not involved in the PSNR calculation.
+        input_order (str): Whether the input order is 'HWC' or 'CHW'.
+            Default: 'HWC'.
+        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.
+
+    Returns:
+        float: psnr result.
+    """
+
+    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
+    if input_order not in ['HWC', 'CHW']:
+        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
+    img1 = reorder_image(img1, input_order=input_order)
+    img2 = reorder_image(img2, input_order=input_order)
+    img1 = img1.astype(np.float64)
+    img2 = img2.astype(np.float64)
+
+    if crop_border != 0:
+        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
+        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]
+
+    if test_y_channel:
+        img1 = to_y_channel(img1)
+        img2 = to_y_channel(img2)
+
+    mse = np.mean((img1 - img2) ** 2)
+    if mse == 0:
+        return float('inf')
+    return 20. * np.log10(255. / np.sqrt(mse))
+
+
+def _ssim(img1, img2):
+    """Calculate SSIM (structural similarity) for one channel images.
+
+    It is called by func:`calculate_ssim`.
+
+    Args:
+        img1 (ndarray): Images with range [0, 255] with order 'HWC'.
+        img2 (ndarray): Images with range [0, 255] with order 'HWC'.
+
+    Returns:
+        float: ssim result.
+    """
+
+    C1 = (0.01 * 255) ** 2
+    C2 = (0.03 * 255) ** 2
+
+    img1 = img1.astype(np.float64)
+    img2 = img2.astype(np.float64)
+    kernel = cv2.getGaussianKernel(11, 1.5)
+    window = np.outer(kernel, kernel.transpose())
+
+    mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5]
+    mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
+    mu1_sq = mu1 ** 2
+    mu2_sq = mu2 ** 2
+    mu1_mu2 = mu1 * mu2
+    sigma1_sq = cv2.filter2D(img1 ** 2, -1, window)[5:-5, 5:-5] - mu1_sq
+    sigma2_sq = cv2.filter2D(img2 ** 2, -1, window)[5:-5, 5:-5] - mu2_sq
+    sigma12 = cv2.filter2D(img1 * img2, -1, window)[5:-5, 5:-5] - mu1_mu2
+
+    ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
+    return ssim_map.mean()
+
+
+def calculate_ssim(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
+    """Calculate SSIM (structural similarity).
+
+    Ref:
+    Image quality assessment: From error visibility to structural similarity
+
+    The results are the same as that of the official released MATLAB code in
+    https://ece.uwaterloo.ca/~z70wang/research/ssim/.
+
+    For three-channel images, SSIM is calculated for each channel and then
+    averaged.
+
+    Args:
+        img1 (ndarray): Images with range [0, 255].
+        img2 (ndarray): Images with range [0, 255].
+        crop_border (int): Cropped pixels in each edge of an image. These
+            pixels are not involved in the SSIM calculation.
+        input_order (str): Whether the input order is 'HWC' or 'CHW'.
+            Default: 'HWC'.
+        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.
+
+    Returns:
+        float: ssim result.
+    """
+
+    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
+    if input_order not in ['HWC', 'CHW']:
+        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
+    img1 = reorder_image(img1, input_order=input_order)
+    img2 = reorder_image(img2, input_order=input_order)
+    img1 = img1.astype(np.float64)
+    img2 = img2.astype(np.float64)
+
+    if crop_border != 0:
+        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
+        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]
+
+    if test_y_channel:
+        img1 = to_y_channel(img1)
+        img2 = to_y_channel(img2)
+
+    ssims = []
+    for i in range(img1.shape[2]):
+        ssims.append(_ssim(img1[..., i], img2[..., i]))
+    return np.array(ssims).mean()
+
+
+def _blocking_effect_factor(im):
+    block_size = 8
+
+    block_horizontal_positions = torch.arange(7, im.shape[3] - 1, 8)
+    block_vertical_positions = torch.arange(7, im.shape[2] - 1, 8)
+
+    horizontal_block_difference = (
+                (im[:, :, :, block_horizontal_positions] - im[:, :, :, block_horizontal_positions + 1]) ** 2).sum(
+        3).sum(2).sum(1)
+    vertical_block_difference = (
+                (im[:, :, block_vertical_positions, :] - im[:, :, block_vertical_positions + 1, :]) ** 2).sum(3).sum(
+        2).sum(1)
+
+    nonblock_horizontal_positions = np.setdiff1d(torch.arange(0, im.shape[3] - 1), block_horizontal_positions)
+    nonblock_vertical_positions = np.setdiff1d(torch.arange(0, im.shape[2] - 1), block_vertical_positions)
+
+    horizontal_nonblock_difference = (
+                (im[:, :, :, nonblock_horizontal_positions] - im[:, :, :, nonblock_horizontal_positions + 1]) ** 2).sum(
+        3).sum(2).sum(1)
+    vertical_nonblock_difference = (
+                (im[:, :, nonblock_vertical_positions, :] - im[:, :, nonblock_vertical_positions + 1, :]) ** 2).sum(
+        3).sum(2).sum(1)
+
+    n_boundary_horiz = im.shape[2] * (im.shape[3] // block_size - 1)
+    n_boundary_vert = im.shape[3] * (im.shape[2] // block_size - 1)
+    boundary_difference = (horizontal_block_difference + vertical_block_difference) / (
+                n_boundary_horiz + n_boundary_vert)
+
+    n_nonboundary_horiz = im.shape[2] * (im.shape[3] - 1) - n_boundary_horiz
+    n_nonboundary_vert = im.shape[3] * (im.shape[2] - 1) - n_boundary_vert
+    nonboundary_difference = (horizontal_nonblock_difference + vertical_nonblock_difference) / (
+                n_nonboundary_horiz + n_nonboundary_vert)
+
+    scaler = np.log2(block_size) / np.log2(min([im.shape[2], im.shape[3]]))
+    bef = scaler * (boundary_difference - nonboundary_difference)
+
+    bef[boundary_difference <= nonboundary_difference] = 0
+    return bef
+
+
+def calculate_psnrb(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
+    """Calculate PSNR-B (Peak Signal-to-Noise Ratio).
+
+    Ref: Quality assessment of deblocked images, for JPEG image deblocking evaluation
+    # https://gitlab.com/Queuecumber/quantization-guided-ac/-/blob/master/metrics/psnrb.py
+
+    Args:
+        img1 (ndarray): Images with range [0, 255].
+        img2 (ndarray): Images with range [0, 255].
+        crop_border (int): Cropped pixels in each edge of an image. These
+            pixels are not involved in the PSNR calculation.
+        input_order (str): Whether the input order is 'HWC' or 'CHW'.
+            Default: 'HWC'.
+        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.
+
+    Returns:
+        float: psnr result.
+    """
+
+    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
+    if input_order not in ['HWC', 'CHW']:
+        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
+    img1 = reorder_image(img1, input_order=input_order)
+    img2 = reorder_image(img2, input_order=input_order)
+    img1 = img1.astype(np.float64)
+    img2 = img2.astype(np.float64)
+
+    if crop_border != 0:
+        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
+        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]
+
+    if test_y_channel:
+        img1 = to_y_channel(img1)
+        img2 = to_y_channel(img2)
+
+    # follow https://gitlab.com/Queuecumber/quantization-guided-ac/-/blob/master/metrics/psnrb.py
+    img1 = torch.from_numpy(img1).permute(2, 0, 1).unsqueeze(0) / 255.
+    img2 = torch.from_numpy(img2).permute(2, 0, 1).unsqueeze(0) / 255.
+
+    total = 0
+    for c in range(img1.shape[1]):
+        mse = torch.nn.functional.mse_loss(img1[:, c:c + 1, :, :], img2[:, c:c + 1, :, :], reduction='none')
+        bef = _blocking_effect_factor(img1[:, c:c + 1, :, :])
+
+        mse = mse.view(mse.shape[0], -1).mean(1)
+        total += 10 * torch.log10(1 / (mse + bef))
+
+    return float(total) / img1.shape[1]
+
+
+def reorder_image(img, input_order='HWC'):
+    """Reorder images to 'HWC' order.
+
+    If the input_order is (h, w), return (h, w, 1);
+    If the input_order is (c, h, w), return (h, w, c);
+    If the input_order is (h, w, c), return as it is.
+
+    Args:
+        img (ndarray): Input image.
+        input_order (str): Whether the input order is 'HWC' or 'CHW'.
+            If the input image shape is (h, w), input_order will not have
+            effects. Default: 'HWC'.
+
+    Returns:
+        ndarray: reordered image.
+    """
+
+    if input_order not in ['HWC', 'CHW']:
+        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' "'HWC' and 'CHW'")
+    if len(img.shape) == 2:
+        img = img[..., None]
+    if input_order == 'CHW':
+        img = img.transpose(1, 2, 0)
+    return img
+
+
+def to_y_channel(img):
+    """Change to Y channel of YCbCr.
+
+    Args:
+        img (ndarray): Images with range [0, 255].
+
+    Returns:
+        (ndarray): Images with range [0, 255] (float type) without round.
+    """
+    img = img.astype(np.float32) / 255.
+    if img.ndim == 3 and img.shape[2] == 3:
+        img = bgr2ycbcr(img, y_only=True)
+        img = img[..., None]
+    return img * 255.
+
+
+def _convert_input_type_range(img):
+    """Convert the type and range of the input image.
+
+    It converts the input image to np.float32 type and range of [0, 1].
+    It is mainly used for pre-processing the input image in colorspace
+    convertion functions such as rgb2ycbcr and ycbcr2rgb.
+
+    Args:
+        img (ndarray): The input image. It accepts:
+            1. np.uint8 type with range [0, 255];
+            2. np.float32 type with range [0, 1].
+
+    Returns:
+        (ndarray): The converted image with type of np.float32 and range of
+            [0, 1].
+    """
+    img_type = img.dtype
+    img = img.astype(np.float32)
+    if img_type == np.float32:
+        pass
+    elif img_type == np.uint8:
+        img /= 255.
+    else:
+        raise TypeError('The img type should be np.float32 or np.uint8, ' f'but got {img_type}')
+    return img
+
+
+def _convert_output_type_range(img, dst_type):
+    """Convert the type and range of the image according to dst_type.
+
+    It converts the image to desired type and range. If `dst_type` is np.uint8,
+    images will be converted to np.uint8 type with range [0, 255]. If
+    `dst_type` is np.float32, it converts the image to np.float32 type with
+    range [0, 1].
+    It is mainly used for post-processing images in colorspace convertion
+    functions such as rgb2ycbcr and ycbcr2rgb.
+
+    Args:
+        img (ndarray): The image to be converted with np.float32 type and
+            range [0, 255].
+        dst_type (np.uint8 | np.float32): If dst_type is np.uint8, it
+            converts the image to np.uint8 type with range [0, 255]. If
+            dst_type is np.float32, it converts the image to np.float32 type
+            with range [0, 1].
+
+    Returns:
+        (ndarray): The converted image with desired type and range.
+    """
+    if dst_type not in (np.uint8, np.float32):
+        raise TypeError('The dst_type should be np.float32 or np.uint8, ' f'but got {dst_type}')
+    if dst_type == np.uint8:
+        img = img.round()
+    else:
+        img /= 255.
+    return img.astype(dst_type)
+
+
+def bgr2ycbcr(img, y_only=False):
+    """Convert a BGR image to YCbCr image.
+
+    The bgr version of rgb2ycbcr.
+    It implements the ITU-R BT.601 conversion for standard-definition
+    television. See more details in
+    https://en.wikipedia.org/wiki/YCbCr#ITU-R_BT.601_conversion.
+
+    It differs from a similar function in cv2.cvtColor: `BGR <-> YCrCb`.
+    In OpenCV, it implements a JPEG conversion. See more details in
+    https://en.wikipedia.org/wiki/YCbCr#JPEG_conversion.
+
+    Args:
+        img (ndarray): The input image. It accepts:
+            1. np.uint8 type with range [0, 255];
+            2. np.float32 type with range [0, 1].
+        y_only (bool): Whether to only return Y channel. Default: False.
+
+    Returns:
+        ndarray: The converted YCbCr image. The output image has the same type
+            and range as input image.
+    """
+    img_type = img.dtype
+    img = _convert_input_type_range(img)
+    if y_only:
+        out_img = np.dot(img, [24.966, 128.553, 65.481]) + 16.0
+    else:
+        out_img = np.matmul(
+            img, [[24.966, 112.0, -18.214], [128.553, -74.203, -93.786], [65.481, -37.797, 112.0]]) + [16, 128, 128]
+    out_img = _convert_output_type_range(out_img, img_type)
+    return out_img