tfmri.image.ssim2d_multiscale

ssim2d_multiscale(img1, img2, max_val=None, power_factors=(0.0448, 0.2856, 0.3001, 0.2363, 0.1333), filter_size=11, filter_sigma=1.5, k1=0.01, k2=0.03, name='ssim2d_multiscale')[source]

Computes the multiscale SSIM (MS-SSIM) between two 2D images.

This function operates on batches of multi-channel inputs and returns an MS-SSIM value for each image in the batch.

Parameters
  • img1 – A Tensor. First batch of images. Must have rank >= 3 with shape batch_shape + [height, width, channels]. height and width must be greater than or equal to (filter_size - 1) * 2 ** (len(power_factors) - 1) + 1. Can have integer or floating point type, with values in the range [0, max_val].

  • img2 – A Tensor. Second batch of images. Must have rank >= 3 with shape batch_shape + [height, width, channels]. height and width must be greater than or equal to (filter_size - 1) * 2 ** (len(power_factors) - 1) + 1. Can have integer or floating point type, with values in the range [0, max_val].

  • max_val – The dynamic range of the images (i.e., the difference between the maximum and the minimum allowed values). Defaults to 1 for floating point input images and MAX for integer input images, where MAX is the largest positive representable number for the data type.

  • power_factors – A list of weights for each of the scales. The length of the list determines the number of scales. Index 0 is the unscaled resolution’s weight and each increasing scale corresponds to the image being downsampled by 2. Defaults to (0.0448, 0.2856, 0.3001, 0.2363, 0.1333), which are the values obtained in the original paper 1.

  • filter_size – The size of the Gaussian filter. Defaults to 11.

  • filter_sigma – The standard deviation of the Gaussian filter. Defaults to 1.5.

  • k1 – Factor used to calculate the regularization constant for the luminance term, as C1 = (k1 * max_val) ** 2. Defaults to 0.01.

  • k2 – Factor used to calculate the regularization constant for the contrast term, as C2 = (k2 * max_val) ** 2. Defaults to 0.03.

  • name – Namespace to embed the computation in.

Returns

A Tensor of type float32 and shape batch_shape containing an MS-SSIM value for each image in the batch.

References

1

Z. Wang, E. P. Simoncelli and A. C. Bovik, “Multiscale structural similarity for image quality assessment,” The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, 2003, pp. 1398-1402 Vol.2, doi: 10.1109/ACSSC.2003.1292216.