basicsr.utils.matlab_functions

basicsr.utils.matlab_functions.calculate_weights_indices(in_length, out_length, scale, kernel, kernel_width, antialiasing)[source]

Calculate weights and indices, used for imresize function.

Parameters:

  • in_length (int) – Input length.

  • out_length (int) – Output length.

  • scale (float) – Scale factor.

  • kernel_width (int) – Kernel width.

  • antialisaing (bool) – Whether to apply anti-aliasing when downsampling.

basicsr.utils.matlab_functions.cubic(x)[source]

cubic function used for calculate_weights_indices.

basicsr.utils.matlab_functions.imresize(img, scale, antialiasing=True)[source]

imresize function same as MATLAB.

It now only supports bicubic. The same scale applies for both height and width.

Parameters:

  • img (Tensor | Numpy array) – Tensor: Input image with shape (c, h, w), [0, 1] range. Numpy: Input image with shape (h, w, c), [0, 1] range.

  • scale (float) – Scale factor. The same scale applies for both height and width.

  • antialisaing (bool) – Whether to apply anti-aliasing when downsampling. Default: True.

Returns:

Output image with shape (c, h, w), [0, 1] range, w/o round.

Return type:

Tensor