pyiqa.archs.ssim_arch
=====================

.. py:module:: pyiqa.archs.ssim_arch

.. autoapi-nested-parse::

   SSIM, MS-SSIM, CW-SSIM Metric

   Created by:
   - https://github.com/dingkeyan93/IQA-optimization/blob/master/IQA_pytorch/SSIM.py
   - https://github.com/dingkeyan93/IQA-optimization/blob/master/IQA_pytorch/MS_SSIM.py
   - https://github.com/dingkeyan93/IQA-optimization/blob/master/IQA_pytorch/CW_SSIM.py

   Modified by: Jiadi Mo (https://github.com/JiadiMo)

   Refer to:
       - Official SSIM matlab code from https://www.cns.nyu.edu/~lcv/ssim/;
       - PIQ from https://github.com/photosynthesis-team/piq;
       - BasicSR from https://github.com/xinntao/BasicSR/blob/master/basicsr/metrics/psnr_ssim.py;
       - Official MS-SSIM matlab code from https://ece.uwaterloo.ca/~z70wang/research/iwssim/msssim.zip;
       - Official CW-SSIM matlab code from
       https://www.mathworks.com/matlabcentral/mlc-downloads/downloads/submissions/43017/versions/1/download/zip;







Module Contents
---------------

.. py:function:: ssim(X, Y, win=None, get_ssim_map=False, get_cs=False, get_weight=False, downsample=False, data_range=1.0)

.. py:class:: SSIM(channels=3, downsample=False, test_y_channel=True, color_space='yiq', crop_border=0.0)

   Bases: :py:obj:`torch.nn.Module`


   Args:
   - channel: number of channel.
   - downsample: boolean, whether to downsample same as official matlab code.
   - test_y_channel: boolean, whether to use y channel on ycbcr same as official matlab code.


   .. py:method:: forward(X, Y)


.. py:function:: ms_ssim(X, Y, win=None, data_range=1.0, downsample=False, test_y_channel=True, is_prod=True, color_space='yiq')

   Compute Multiscale structural similarity for a batch of images.
   :param x: An input tensor. Shape :math:`(N, C, H, W)`.
   :param y: A target tensor. Shape :math:`(N, C, H, W)`.
   :param win: Window setting.
   :param downsample: Boolean, whether to downsample which mimics official SSIM matlab code.
   :param test_y_channel: Boolean, whether to use y channel on ycbcr.
   :param is_prod: Boolean, calculate product or sum between mcs and weight.

   :returns: Index of similarity between two images. Usually in [0, 1] interval.


.. py:class:: MS_SSIM(channels=3, downsample=False, test_y_channel=True, is_prod=True, color_space='yiq')

   Bases: :py:obj:`torch.nn.Module`


   Multiscale structure similarity

   .. rubric:: References

   Wang, Zhou, Eero P. Simoncelli, and Alan C. Bovik. "Multiscale structural similarity for image
   quality assessment." In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers,
   2003, vol. 2, pp. 1398-1402. Ieee, 2003.

   :param channel: Number of channel.
   :param downsample: Boolean, whether to downsample which mimics official SSIM matlab code.
   :param test_y_channel: Boolean, whether to use y channel on ycbcr which mimics official matlab code.


   .. py:method:: forward(X, Y)

      Computation of MS-SSIM metric.
      :param x: An input tensor. Shape :math:`(N, C, H, W)`.
      :param y: A target tensor. Shape :math:`(N, C, H, W)`.

      :returns: Value of MS-SSIM metric in [0, 1] range.



.. py:class:: CW_SSIM(channels=1, level=4, ori=8, guardb=0, K=0, test_y_channel=True, color_space='yiq')

   Bases: :py:obj:`torch.nn.Module`


   Complex-Wavelet Structural SIMilarity (CW-SSIM) index.

   .. rubric:: References

   M. P. Sampat, Z. Wang, S. Gupta, A. C. Bovik, M. K. Markey.
   "Complex Wavelet Structural Similarity: A New Image Similarity Index",
   IEEE Transactions on Image Processing, 18(11), 2385-401, 2009.

   :param - channel: Number of channel.
   :param - test_y_channel: Boolean, whether to use y channel on ycbcr.
   :param - level: The number of levels to used in the complex steerable pyramid decomposition
   :param - ori: The number of orientations to be used in the complex steerable pyramid decomposition
   :param - guardb: How much is discarded from the four image boundaries.
   :param - K: the constant in the CWSSIM index formula (see the above reference) default value: K=0


   .. py:method:: conj(x, y)


   .. py:method:: conv2d_complex(x, win, groups=1)


   .. py:method:: cw_ssim(x, y, test_y_channel)

      Compute CW-SSIM for a batch of images.
      :param x: An input tensor. Shape :math:`(N, C, H, W)`.
      :param y: A target tensor. Shape :math:`(N, C, H, W)`.
      :param test_y_channel: Boolean, whether to use y channel on ycbcr.

      :returns: Index of similarity between two images. Usually in [0, 1] interval.



   .. py:method:: forward(X, Y)

      Computation of CW-SSIM metric.
      :param X: An input tensor. Shape :math:`(N, C, H, W)`.
      :param Y: A target tensor. Shape :math:`(N, C, H, W)`.

      :returns: Value of CW-SSIM metric in [0, 1] range.