deepinv.physics#
This module provides a set of forward operators for various imaging modalities. Please refer to the Operators & Noise section for more details.
Base Classes#
User Guide: refer to Introduction for more information.
Parent class for forward operators |
|
Parent class for linear operators. |
|
Parent class for linear operators with SVD decomposition. |
Base class for parameter generation of physics parameters. |
|
Base class for mixing multiple |
Operators#
User Guide: refer to Operators for more information.
Forward operator for denoising problems. |
|
Inpainting forward operator, keeps a subset of entries. |
|
Converts RGB images to grayscale. |
|
Demosaicing operator. |
|
Blur operator. |
|
FFT-based blur operator. |
|
Implements a space varying blur via product-convolution. |
|
Downsampling operator for super-resolution problems. |
|
Single-coil accelerated 2D or 3D magnetic resonance imaging. |
|
Mixin base class for MRI functionality. |
|
Single-coil accelerated dynamic magnetic resonance imaging. |
|
Multi-coil 2D or 3D MRI operator. |
|
Single-coil accelerated magnetic resonance imaging using sequential sampling. |
|
(Computed) Tomography operator. |
|
Pansharpening forward operator. |
|
Compressed Sensing forward operator. |
|
Structured random linear operator model corresponding to the operator |
|
Single pixel imaging camera. |
|
Radio Interferometry measurement operator. |
|
Single photon lidar operator for depth ranging. |
|
Standard haze model |
|
Phase Retrieval base class corresponding to the operator |
|
Random Phase Retrieval forward operator. |
|
Structured random phase retrieval model corresponding to the operator |
Base generator for splitting/inpainting masks. |
|
Randomly generate Gaussian splitting/inpainting masks. |
|
Phase2Phase splitting mask generator for dynamic data. |
|
|
Artifact2Artifact splitting mask generator for dynamic data. |
Random motion blur generator. |
|
Diffraction limited blur generator. |
|
3D diffraction limited kernels using Zernike decomposition of the phase mask. |
|
Generates parameters of space-varying blurs. |
|
Base generator for MRI acceleration masks. |
|
Generator for MRI Cartesian acceleration masks using Gaussian undersampling. |
|
Generator for MRI Cartesian acceleration masks using random uniform undersampling. |
|
Generator for MRI Cartesian acceleration masks using uniform (equispaced) non-random undersampling with random offset. |
Gaussian blur filter. |
|
Bilinear filter. |
|
Bicubic filter. |
|
Anti-aliasing sinc filter multiplied by a Kaiser window. |
Noise distributions#
User Guide: refer to Noise distributions for more information.
Gaussian noise \(y=z+\epsilon\) where \(\epsilon\sim \mathcal{N}(0,I\sigma^2)\). |
|
Log-Poisson noise \(y = \frac{1}{\mu} \log(\frac{\mathcal{P}(\exp(-\mu x) N_0)}{N_0})\). |
|
Poisson noise \(y = \mathcal{P}(\frac{x}{\gamma})\) with gain \(\gamma>0\). |
|
Poisson-Gaussian noise \(y = \gamma z + \epsilon\) where \(z\sim\mathcal{P}(\frac{x}{\gamma})\) and \(\epsilon\sim\mathcal{N}(0, I \sigma^2)\). |
|
Uniform noise \(y = x + \epsilon\) where \(\epsilon\sim\mathcal{U}(-a,a)\). |
|
Gaussian noise \(y=z+\epsilon\) where \(\epsilon\sim \mathcal{N}(0,I\sigma^2)\) and \(\sigma \sim\mathcal{U}(\sigma_{\text{min}}, \sigma_{\text{max}})\) |
|
Gamma noise \(y = \mathcal{G}(\ell, x/\ell)\) |
|
Generator for the noise level \(\sigma\) in the Gaussian noise model. |
Base class for temporal capabilities for physics and models. |
|
Provides the adjoint function of a linear operator \(A\), i.e., \(A^{\top}\). |
Functional#
User Guide: refer to Functional for more information.
A helper function performing the 2d convolution of images |
|
A helper function performing the 2d transposed convolution 2d of x and filter. |
|
A helper function performing the 2d convolution of images |
|
A helper function performing the 2d transposed convolution 2d of |
|
A helper function performing the 3d convolution of |
|
A helper function performing the 3d transposed convolution of |
|
Product-convolution operator in 2d. |
|
Implements diagonal matrices or multipliers \(x\) and mult. |
|
Implements the adjoint of diagonal matrices or multipliers \(x\) and mult. |
|
Sparse Radon transform operator. |
|
Inverse sparse Radon transform operator. |
|
Computes the multidimensional histogram of a tensor. |
|
Computes the histogram of a tensor. |