Upsampling#

class deepinv.physics.Upsampling(img_size, filter=None, factor=2, padding='circular', device='cpu', **kwargs)[source]#

Bases: Downsampling

Upsampling operator.

This operator performs the operation

\[y = h^T * S^T (x)\]

where \(S^T\) is the adjoint of the subsampling operator and \(h\) is a low-pass filter.

Parameters:
  • filter (torch.Tensor, str, None) – Upsampling filter. It can be 'gaussian', 'bilinear', 'bicubic', 'sinc' or a custom torch.Tensor filter. If None, no filtering is applied.

  • img_size (tuple[int]) – size of the output image

  • factor (int) – upsampling factor

  • padding (str) – options are 'circular', 'replicate' and 'reflect'.

  • device (str) – cpu or cuda