User Guide#
Imaging inverse problems are described by the equation \(y = \noise{\forw{x}}\) where \(x\) is an unknown signal (image, volume, etc.) we want to recover, \(y\) are the observed measurements, \(A\) is a deterministic (linear or non-linear) operator capturing the physics of the acquisition and \(N\) characterizes the noise affecting the measurements.
Operators#
The library provides a large variety of imaging operators physics modelling \(\noise{\forw{\cdot}}\),
which can simulate the observation process:
x = load_image()
y = physics(x) # simulate observation
Introduction
Introduction to the physics package.
Operators
Forward operators and noise distributions.
Defining your operator
How to define your own forward operator, if the existing ones are not enough.
Functional
Various utilities for forward operators.
Reconstruction#
In order to recover an image from its measurements, the library provides many
reconstruction methods \(\hat{x}=R(y, A)\), which often leverage knowledge of the acquisition physics.
Given a restoration model model, the reconstruction is therefore provided as
x_hat = model(y, physics) # reconstruct signal
Introduction
Introduction and summary of reconstruction algorithms.
Denoisers
Classical and deep denoisers with pretrained weights.
Artifact Removal
Reconstruction networks from denoisers and other image-to-image networks.
Optimization
Priors and data-fidelity functions, and optimization algorithms.
Unfolded Algorithms
Unfolded architectures.
Iterative Reconstruction
Plug-and-play, RED, variational methods.
Adversarial Reconstruction
Conditional, unconditional GANs and deep image prior.
Sampling
Diffusion and MCMC algorithms.
Training, Testing and Utilities#
All the tools from the library, from measurement operator to restoration methods,
are implemented as torch.nn.Module and therefore natively support backpropagation.
Reconstruction networks model can be trained on datasets to improve their performance:
trainer = Trainer(model, loss, optimizer, metric, train_dataset, ...)
trainer.train()
trainer.test(test_dataset)
Training
Training and testing reconstruction models.
Datasets
Utilities to generate and load datasets for training and testing.
Loss
Supervised and self-supervised losses to train the models.
Metrics
Distortion and perceptual metrics to evaluate reconstructions.
Transforms
Transforms for data augmentation and self-supervised learning.
Utils
Plotting and other utilities.