Examples

All the examples have a download link at the end. You can load the example’s notebook on Google Colab and run them by adding the line

pip install git+https://github.com/deepinv/deepinv.git#egg=deepinv

to the top of the notebook (e.g., as in here).

Get started

Get started with the 5 minute quickstart tutorial, or view it in Colab here.

Basics

5 minute quickstart tutorial

5 minute quickstart tutorial

Use a pretrained model

Use a pretrained model

Use iterative reconstruction algorithms

Use iterative reconstruction algorithms

Bring your own dataset

Bring your own dataset

Bring your own physics

Bring your own physics

Models

Inference and fine-tune a foundation model

Inference and fine-tune a foundation model

Training a reconstruction model

Training a reconstruction model

Benchmarking pretrained denoisers

Benchmarking pretrained denoisers

Super-resolution with SRResNet

Super-resolution with SRResNet

Reconstruct undersampled k-space for cardiac and brain MRI

Reconstruct undersampled k-space for cardiac and brain MRI

Reconstruct prospectively-undersampled raw multicoil MRI

Reconstruct prospectively-undersampled raw multicoil MRI

Physics

Tour of forward sensing operators

Tour of forward sensing operators

Tour of blur operators

Tour of blur operators

Tour of MRI functionality in DeepInverse

Tour of MRI functionality in DeepInverse

Tour of ultrafast ultrasound in DeepInverse

Tour of ultrafast ultrasound in DeepInverse

3D diffraction PSF

3D diffraction PSF

Random phase retrieval and reconstruction methods.

Random phase retrieval and reconstruction methods.

Spectral Methods for Non-Circular Deblurring with Liu-Jia Padding

Spectral Methods for Non-Circular Deblurring with Liu-Jia Padding

3D PET reconstruction with the Brainweb dataset

3D PET reconstruction with the Brainweb dataset

Positron emission tomography (PET) in 3D

Positron emission tomography (PET) in 3D

Inverse scattering problem

Inverse scattering problem

Single photon lidar operator for depth ranging.

Single photon lidar operator for depth ranging.

Ptychography phase retrieval

Ptychography phase retrieval

Positron emission tomography (PET) in 2D

Positron emission tomography (PET) in 2D

Spatial unwrapping and modulo imaging

Spatial unwrapping and modulo imaging

Remote sensing with satellite images

Remote sensing with satellite images

2D PET reconstruction with the Brainweb dataset

2D PET reconstruction with the Brainweb dataset

Poisson-Gaussian Denoising with the Generalized Anscombe Transform

Poisson-Gaussian Denoising with the Generalized Anscombe Transform

Pattern Ordering in a Compressive Single Pixel Camera

Pattern Ordering in a Compressive Single Pixel Camera

Optimization

3D denoising of brain MRI with wavelet and TV priors

3D denoising of brain MRI with wavelet and TV priors

Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting

Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting

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.

Image inpainting with wavelet prior

Image inpainting with wavelet prior

Multispectral demosaicing from raw sensor data

Multispectral demosaicing from raw sensor data

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)

Reconstructing an image using the deep image prior.

Reconstructing an image using the deep image prior.

Plug-and-Play

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

In-vivo ultrafast ultrasound reconstruction with Plug-and-Play

In-vivo ultrafast ultrasound reconstruction with Plug-and-Play

Multi-scale Plug-and-Play for Inpainting

Multi-scale Plug-and-Play for Inpainting

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

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

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

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

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).

Diffusion & MCMC

Building your custom MCMC sampling algorithm.

Building your custom MCMC sampling algorithm.

Building your diffusion posterior sampling method using SDEs

Building your diffusion posterior sampling method using SDEs

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

Image reconstruction with a diffusion model

Image reconstruction with a diffusion model

Implementing DiffPIR

Implementing DiffPIR

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.

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

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

Unfolded

DEAL denoising and reconstruction

DEAL denoising and reconstruction

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring

Learned Iterative Soft-Thresholding Algorithm (LISTA) for compressed sensing

Learned Iterative Soft-Thresholding Algorithm (LISTA) for compressed sensing

Learned Primal-Dual algorithm for CT scan.

Learned Primal-Dual algorithm for CT scan.

Learned iterative custom prior

Learned iterative custom prior

Reducing the memory and computational complexity of unfolded network training

Reducing the memory and computational complexity of unfolded network training

Unfolded Chambolle-Pock for constrained image inpainting

Unfolded Chambolle-Pock for constrained image inpainting

Vanilla Unfolded algorithm for super-resolution

Vanilla Unfolded algorithm for super-resolution

Blind Inverse Problems

Blind Richardson-Lucy deconvolution

Blind Richardson-Lucy deconvolution

Blind deblurring with kernel estimation network

Blind deblurring with kernel estimation network

Blind denoising with noise level estimation

Blind denoising with noise level estimation

Calibrating physics operators

Calibrating physics operators

Self-Supervised Learning

Image transformations for Equivariant Imaging

Image transformations for Equivariant Imaging

Low-field MRI denoising without ground truth

Low-field MRI denoising without ground truth

Poisson denoising using Poisson2Sparse

Poisson denoising using Poisson2Sparse

Scan-specific zero-shot SSDU for MRI

Scan-specific zero-shot SSDU for MRI

Self-supervised MRI reconstruction with Artifact2Artifact

Self-supervised MRI reconstruction with Artifact2Artifact

Self-supervised denoising with the Generalized R2R loss.

Self-supervised denoising with the Generalized R2R loss.

Self-supervised denoising with the Neighbor2Neighbor loss.

Self-supervised denoising with the Neighbor2Neighbor loss.

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.

Self-supervised learning from incomplete measurements of multiple operators.

Self-supervised learning from incomplete measurements of multiple operators.

Self-supervised learning with Equivariant Imaging for MRI.

Self-supervised learning with Equivariant Imaging for MRI.

Self-supervised learning with Equivariant Splitting

Self-supervised learning with Equivariant Splitting

Self-supervised learning with measurement splitting

Self-supervised learning with measurement splitting

Ultrasound despeckling from B-mode images

Ultrasound despeckling from B-mode images

Transformations & Equivariance

Image transforms for equivariance & augmentations

Image transforms for equivariance & augmentations

Adversarial Learning

Imaging inverse problems with adversarial networks

Imaging inverse problems with adversarial networks

External Libraries

Loading scientific images

Loading scientific images

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

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

Low-intensity STED fluorescence microscopy denoising

Low-intensity STED fluorescence microscopy denoising

Radio interferometric imaging with deepinverse

Radio interferometric imaging with deepinverse

Reconstruct accelerated non-Cartesian breast MRI acquisition data

Reconstruct accelerated non-Cartesian breast MRI acquisition data

Reconstruct real CT sinograms with the 2DeteCT benchmark

Reconstruct real CT sinograms with the 2DeteCT benchmark

Single-pixel imaging with Spyrit

Single-pixel imaging with Spyrit

Using HuggingFace datasets

Using HuggingFace datasets

Distributed Computing

Distributed Denoiser with Image Tiling

Distributed Denoiser with Image Tiling

Distributed Physics Operators

Distributed Physics Operators

Distributed Plug-and-Play (PnP) Reconstruction

Distributed Plug-and-Play (PnP) Reconstruction

Distributed Training of Unfolded Networks

Distributed Training of Unfolded Networks

Metrics

Blind inverse problems with no reference metrics

Blind inverse problems with no reference metrics

Fitting NIQE on a custom dataset

Fitting NIQE on a custom dataset