pyiqa.archs.vif_arch
====================

.. py:module:: pyiqa.archs.vif_arch

.. autoapi-nested-parse::

   VIF Metric

   @article{sheikh2006vif,
     title={Image information and visual quality},
     author={Sheikh, Hamid R and Bovik, Alan C},
     journal={IEEE Transactions on image processing},
     volume={15},
     number={2},
     pages={430--444},
     year={2006},
     publisher={IEEE}
   }

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

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

   Refer to:
       Matlab code from http://live.ece.utexas.edu/research/Quality/vifvec_release.zip;







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

.. py:function:: sp5_filters()

   Define spatial filters.


.. py:function:: corrDn(image, filt, step=1, channels=1)

   Compute correlation of image with FILT, followed by downsampling.
   :param image: A tensor. Shape :math:`(N, C, H, W)`.
   :param filt: A filter.
   :param step: Downsampling factors.
   :param channels: Number of channels.


.. py:function:: SteerablePyramidSpace(image, height=4, order=5, channels=1)

   Construct a steerable pyramid on image.
   :param image: A tensor. Shape :math:`(N, C, H, W)`.
   :param height: Number of pyramid levels to build.
   :type height: int
   :param order: Number of orientations.
   :type order: int
   :param channels: Number of channels.
   :type channels: int


.. py:class:: VIF(channels=1, level=4, ori=6)

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


   Image Information and Visual Quality metric
   :param channels: Number of channels.
   :type channels: int
   :param level: Number of levels to build.
   :type level: int
   :param ori: Number of orientations.
   :type ori: int

   Reference:
       Sheikh, Hamid R., and Alan C. Bovik. "Image information and visual quality."
       IEEE Transactions on image processing 15, no. 2 (2006): 430-444.


   .. py:method:: corrDn_win(image, filt, step=1, channels=1, start=[0, 0], end=[0, 0])

      Compute correlation of image with FILT using window, followed by downsampling.
      :param image: A tensor. Shape :math:`(N, C, H, W)`.
      :param filt: A filter.
      :param step: Downsampling factors.
      :type step: int
      :param channels: Number of channels.
      :type channels: int
      :param start: The window over which the convolution occurs.
      :type start: list
      :param end: The window over which the convolution occurs.
      :type end: list



   .. py:method:: vifsub_est_M(org, dist)

      Calculate the parameters of the distortion channel.
      :param org: A reference tensor. Shape :math:`(N, C, H, W)`.
      :param dist: A distortion tensor. Shape :math:`(N, C, H, W)`.



   .. py:method:: refparams_vecgsm(org)

      Calculate the parameters of the reference image.
      :param org: A reference tensor. Shape :math:`(N, C, H, W)`.



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

      VIF metric. Order of input is important.
      :param x: A distortion tensor. Shape :math:`(N, C, H, W)`.
      :param y: A reference tensor. Shape :math:`(N, C, H, W)`.



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

      Args:
      x: A distortion tensor. Shape :math:`(N, C, H, W)`.
      y: A reference tensor. Shape :math:`(N, C, H, W)`.
      Order of input is important.