BlurFFT

class deepinv.physics.BlurFFT(img_size, filter=None, device='cpu', **kwargs)[source]

Bases: DecomposablePhysics

FFT-based blur operator.

It performs the operation

\[y = w*x\]

where \(*\) denotes convolution and \(w\) is a filter.

Blur operator based on torch.fft operations, which assumes a circular padding of the input, and allows for the singular value decomposition via deepinv.Physics.DecomposablePhysics and has fast pseudo-inverse and prox operators.

Parameters:
  • img_size (tuple) – Input image size in the form (C, H, W).

  • filter (torch.Tensor) – torch.Tensor of size (1, c, h, w) containing the blur filter with h<=H, w<=W and c=1 or c=C e.g., deepinv.physics.blur.gaussian_filter().

  • device (str) – cpu or cuda


Examples:

BlurFFT operator with a basic averaging filter applied to a 16x16 black image with a single white pixel in the center:

>>> from deepinv.physics import BlurFFT
>>> x = torch.zeros((1, 1, 16, 16)) # Define black image of size 16x16
>>> x[:, :, 8, 8] = 1 # Define one white pixel in the middle
>>> filter = torch.ones((1, 1, 2, 2)) / 4 # Basic 2x2 filter
>>> physics = BlurFFT(filter=filter, img_size=(1, 1, 16, 16))
>>> y = physics(x)
>>> y[y<1e-5] = 0.
>>> y[:, :, 7:10, 7:10] # Display the center of the blurred image
tensor([[[[0.2500, 0.2500, 0.0000],
          [0.2500, 0.2500, 0.0000],
          [0.0000, 0.0000, 0.0000]]]])
A(x, filter=None, **kwargs)[source]

Applies the forward operator \(y = A(x)\).

If a mask/singular values is provided, it is used to apply the forward operator, and also stored as the current mask/singular values.

Parameters:
  • x (torch.Tensor) – input tensor

  • mask (torch.nn.Parameter, float) – singular values.

Returns:

(torch.Tensor) output tensor

A_adjoint(x, filter=None, **kwargs)[source]

Computes the adjoint of the forward operator \(\tilde{x} = A^{\top}y\).

If a mask/singular values is provided, it is used to apply the adjoint operator, and also stored as the current mask/singular values.

Parameters:
  • y (torch.Tensor) – input tensor

  • mask (torch.nn.Parameter, float) – singular values.

Returns:

(torch.Tensor) output tensor

update_parameters(filter=None, **kwargs)[source]

Updates the current filter.

Parameters:

filter (torch.Tensor) – New filter to be applied to the input image.

Examples using BlurFFT:

Image deblurring with custom deep explicit prior.

Image deblurring with custom deep explicit prior.

A tour of blur operators

A tour of blur operators

Image deblurring with Total-Variation (TV) prior

Image deblurring with Total-Variation (TV) prior

Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.

Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

Building your custom sampling algorithm.

Building your custom sampling algorithm.

Implementing DiffPIR

Implementing DiffPIR

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring