NoiseModel

class deepinv.physics.NoiseModel(noise_model=None, rng=None)

Bases: Module

Base class for noise model.

Noise models can be combined via deepinv.physics.NoiseModel.__mul__().

Parameters:

• noise_model (Callable) – noise model function \(N(y)\).

• rng (torch.Generator, None) – (optional) a pseudorandom random number generator for the parameter generation. If provided, it should be on the same device as the input.

__mul__(other)

Concatenates two noise \(N = N_1 \circ N_2\) via the mul operation

The resulting operator will add the noise from both noise models and keep the rng of \(N_1\).

Parameters:

other (deepinv.physics.NoiseModel) – Physics operator \(A_2\)

Returns:

(deepinv.physics.NoiseModel) concatenated operator

forward(input, seed=None)

Add noise to the input

Parameters:

• input (torch.Tensor) – input tensor

• seed (int) – the seed for the random number generator.

rand_like(input, seed=None)

Equivalent to torch.rand_like but supports a pseudorandom number generator argument.

Parameters:

seed (int) – the seed for the random number generator, if rng is provided.

randn_like(input, seed=None)

Equivalent to torch.randn_like but supports a pseudorandom number generator argument.

Parameters:

seed (int) – the seed for the random number generator, if rng is provided.

reset_rng()

Reset the random number generator to its initial state.

rng_manual_seed(seed=None)

Sets the seed for the random number generator.

Parameters:

seed (int) – the seed to set for the random number generator. If not provided, the current state of the random number generator is used. .. note:: The seed will be ignored if the random number generator is not initialized.

update_parameters(**kwargs)

Update the parameters of the noise model.

Parameters:

kwargs (dict) – dictionary of parameters to update.

Examples using NoiseModel:

Bring your own physics

Bring your own physics

Use a pretrained model

Use a pretrained model

5 minute quickstart tutorial

5 minute quickstart tutorial

Blind Richardson-Lucy deconvolution

Blind Richardson-Lucy deconvolution

Calibrating physics operators

Calibrating physics operators

Distributed Plug-and-Play (PnP) Reconstruction

Distributed Plug-and-Play (PnP) Reconstruction

Distributed Training of Unfolded Networks

Distributed Training of Unfolded Networks

Reconstruct real CT sinograms with the 2DeteCT benchmark

Reconstruct real CT sinograms with the 2DeteCT benchmark

Low-dose CT with ASTRA backend and Total-Variation (TV) prior

Low-dose CT with ASTRA backend and Total-Variation (TV) prior

Reconstruct accelerated non-Cartesian breast MRI acquisition data

Reconstruct accelerated non-Cartesian breast MRI acquisition data

Blind inverse problems with no reference metrics

Blind inverse problems with no reference metrics

Inference and fine-tune a foundation model

Inference and fine-tune a foundation model

Reconstruct prospectively-undersampled raw multicoil MRI

Reconstruct prospectively-undersampled raw multicoil MRI

3D denoising of brain MRI with wavelet and TV priors

3D denoising of brain MRI with wavelet and TV priors

Image deblurring with Total-Variation (TV) prior

Image deblurring with Total-Variation (TV) prior

Image deblurring with custom deep explicit prior.

Image deblurring with custom deep explicit prior.

Reconstructing an image using the deep image prior.

Reconstructing an image using the deep image prior.

Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting

Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting

Patch priors for limited-angle computed tomography

Patch priors for limited-angle computed tomography

Poisson Inverse Problems with Maximum-Likelihood Expectation-Maximization (MLEM)

Poisson Inverse Problems with Maximum-Likelihood Expectation-Maximization (MLEM)

Image inpainting with wavelet prior

Image inpainting with wavelet prior

Poisson-Gaussian Denoising with the Generalized Anscombe Transform

Poisson-Gaussian Denoising with the Generalized Anscombe Transform

Tour of forward sensing operators

Tour of forward sensing operators

Spatial unwrapping and modulo imaging

Spatial unwrapping and modulo imaging

Pattern Ordering in a Compressive Single Pixel Camera

Pattern Ordering in a Compressive Single Pixel Camera

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

PnP with custom optimization algorithm (Primal-Dual Condat-Vu)

PnP with custom optimization algorithm (Primal-Dual Condat-Vu)

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

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

Multi-scale Plug-and-Play for Inpainting

Multi-scale Plug-and-Play for Inpainting

Regularization by Denoising (RED) for Super-Resolution.

Regularization by Denoising (RED) for Super-Resolution.

Vanilla PnP for computed tomography (CT).

Vanilla PnP for computed tomography (CT).

Building your custom MCMC sampling algorithm.

Building your custom MCMC sampling algorithm.

Image reconstruction with a diffusion model

Image reconstruction with a diffusion model

Implementing DiffPIR

Implementing DiffPIR

Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse

Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse

DPS – Posterior Sampling with Diffusion Models

DPS -- Posterior Sampling with Diffusion Models

Flow-Matching for posterior sampling and unconditional generation

Flow-Matching for posterior sampling and unconditional generation

Noisy data-fidelity terms for diffusion posterior sampling

Noisy data-fidelity terms for diffusion posterior sampling

Uncertainty quantification with PnP-ULA.

Uncertainty quantification with PnP-ULA.

Low-field MRI denoising without ground truth

Low-field MRI denoising without ground truth

Self-supervised denoising with the Neighbor2Neighbor loss.

Self-supervised denoising with the Neighbor2Neighbor loss.

Poisson denoising using Poisson2Sparse

Poisson denoising using Poisson2Sparse

Self-supervised denoising with the Generalized R2R loss.

Self-supervised denoising with the Generalized R2R loss.

Scan-specific zero-shot SSDU for MRI

Scan-specific zero-shot SSDU for MRI

Self-supervised learning with measurement splitting

Self-supervised learning with measurement splitting

Self-supervised denoising with the SURE loss.

Self-supervised denoising with the SURE loss.

Self-supervised denoising with the UNSURE loss.

Self-supervised denoising with the UNSURE loss.

Image transforms for equivariance & augmentations

Image transforms for equivariance & augmentations

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring

DEAL denoising and reconstruction

DEAL denoising and reconstruction

Learned Primal-Dual algorithm for CT scan.

Learned Primal-Dual algorithm for CT scan.

Reducing the memory and computational complexity of unfolded network training

Reducing the memory and computational complexity of unfolded network training

Vanilla Unfolded algorithm for super-resolution

Vanilla Unfolded algorithm for super-resolution