FisherTippettNoise#

class deepinv.physics.FisherTippettNoise(l=1.0)[source]#

Bases: NoiseModel

Fisher-Tippett noise \(p(y\vert x) = \frac{\ell^{\ell}}{\Gamma(\ell)}\mathrm{e}^{\ell(y-x)}\mathrm{e}^{-\ell\mathrm{e}^{(y-x)}}\)

Distribution for modelling the noise of log-intensities images in SAR imaging.

Warning

This noise model does not support the random number generator.

Parameters:

l (float, torch.Tensor) – noise level.

forward(x, l=None, **kwargs)[source]#

Adds the noise to measurements x

Parameters:

  • x (torch.Tensor) – measurements (log-intensities)

  • l (None, float, torch.Tensor) – noise level. If not None, it will overwrite the current noise level.

Returns:

noisy measurements (log-intensities)