:orphan:

.. _examples:

Examples
========

All the examples have a download link at the end. You can load the example's notebook on
`Google Colab <https://colab.research.google.com/>`_ 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 <https://colab.research.google.com/drive/1ZPKikFM_dov9f-9g2j_S9MIpJSCIk7QF?usp=sharing>`_).




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. thumbnail-parent-div-close

.. raw:: html

    </div>

Basics
------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example we show how to use the deepinv.physics.SinglePhotonLidar forward model.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_lidar_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_lidar.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Single photon lidar operator for depth ranging.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This code shows how to reconstruct a noisy and incomplete image using the deep image prior.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_dip_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_dip.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Reconstructing an image using the deep image prior.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to create your own dataset for deep image inverse problems from a base dataset of images. Here we use Set3C as a base dataset of natural images. This base dataset contains 3 images.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_dataset_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_dataset.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Creating your own dataset</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We demonstrate the use of our deepinv.transform module for use in solving imaging problems. These can be used for:">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_transforms_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_transforms.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image transforms for equivariance & augmentations</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="| This simple example shows how to load and prepare properly a huggingface dataset. | Context: having a quick access to several datasets available under the huggingface format. | Available datasets: https://huggingface.co/datasets?search=deepinv">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_hf_dataset_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_hf_dataset.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Using huggingface dataset</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to create a Ptychography phase retrieval operator and generate phaseless measurements from a given image.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_ptychography_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_ptychography.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Ptychography phase retrieval</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="While deepinv offers a large number of forward operators in the physics module, you might want to create your own forward operator for your specific imaging problem. This example walks you through the creation of a custom forward operator.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_physics_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_physics.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Creating a forward operator.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example we demonstrate remote sensing inverse problems for multispectral satellite imaging.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_remote_sensing_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_remote_sensing.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Remote sensing with satellite images</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example provides a tour of 3D blur operators in the library. In particular, we show how to use Diffraction Blurs (Fresnel diffraction) to simulate fluorescence microscopes.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_microscopy_3d_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_microscopy_3d.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">3D diffraction PSF</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to train a simple reconstruction network for an image inpainting inverse problem.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_train_inpainting_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_train_inpainting.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Training a reconstruction network.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example provides a tour of some of the forward operators implemented in DeepInverse. We restrict ourselves to operators where the signal is a 2D image. The full list of operators can be found in here.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_physics_tour_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_physics_tour.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">A tour of forward sensing operators</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example, we show how to solve a deblurring inverse problem using an explicit prior.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_custom_prior_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_custom_prior.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image deblurring with custom deep explicit prior.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Models can be saved and loaded in the same way as in PyTorch. In this example, we show how to define, load and save a model. For the purpose of the example, we choose an unfolded Chambolle Pock algorithm as the model. The architecture of the model and its training are described in the constrained unfolded demo.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_loading_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_loading.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Saving and loading models</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example provides a tour of 2D blur operators in DeepInv. In particular, we show how to use DiffractionBlurs (Fresnel diffraction), motion blurs and space varying blurs.">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_blur_tour_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_blur_tour.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">A tour of blur operators</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to create a random phase retrieval operator and generate phaseless measurements from a given image. The example showcases 4 different reconstruction methods to recover the image from the phaseless measurements:">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_phase_retrieval_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_phase_retrieval.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Random phase retrieval and reconstruction methods.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example presents the various datasets, forward physics and models available in DeepInverse for Magnetic Resonance Imaging (MRI) problems:">

.. only:: html

  .. image:: /auto_examples/basics/images/thumb/sphx_glr_demo_tour_mri_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_basics_demo_tour_mri.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Tour of MRI functionality in DeepInverse</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Optimization
------------


.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use a standard TV prior for image deblurring. The problem writes as y = Ax + \epsilon where A is a convolutional operator and \epsilon is the realization of some Gaussian noise. The goal is to recover the original image x from the blurred and noisy image y. The TV prior is used to regularize the problem.">

.. only:: html

  .. image:: /auto_examples/optimization/images/thumb/sphx_glr_demo_TV_minimisation_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_optimization_demo_TV_minimisation.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image deblurring with Total-Variation (TV) prior</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use a standard wavelet prior for image inpainting. The problem writes as y = Ax + \epsilon where A is a mask and \epsilon is the realization of some Gaussian noise. The goal is to recover the original image x from the blurred and noisy image y. The wavelet prior is used to regularize the problem.">

.. only:: html

  .. image:: /auto_examples/optimization/images/thumb/sphx_glr_demo_wavelet_prior_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_optimization_demo_wavelet_prior.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image inpainting with wavelet prior</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use a 3D wavelet denoiser for denoising a 3D image. We first apply a standard soft-thresholding wavelet denoiser to a 3D brain MRI volume. We then extend the denoiser objective to a redundant dictionary of wavelet bases, which does not admit a closed-form solution. We solve the denoising problem using the Dykstra-like algorithm.">

.. only:: html

  .. image:: /auto_examples/optimization/images/thumb/sphx_glr_demo_3D_wavelets_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_optimization_demo_3D_wavelets.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">3D wavelet denoising</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Plug-and-Play
-------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This is a simple example to show how to use a mirror descent algorithm for solving an inverse problem with Poisson noise.">

.. only:: html

  .. image:: /auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_mirror_descent_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_plug-and-play_demo_PnP_mirror_descent.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use a standart PnP algorithm with DnCNN denoiser for computed tomography.">

.. only:: html

  .. image:: /auto_examples/plug-and-play/images/thumb/sphx_glr_demo_vanilla_PnP_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_plug-and-play_demo_vanilla_PnP.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Vanilla PnP for computed tomography (CT).</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use the DPIR method to solve a PnP image deblurring problem. The DPIR method is described in the following paper: Zhang, K., Zuo, W., Gu, S., &amp; Zhang, L. (2017). Learning deep CNN denoiser prior for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3929-3938).">

.. only:: html

  .. image:: /auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_DPIR_deblur_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_plug-and-play_demo_PnP_DPIR_deblur.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">DPIR method for PnP image deblurring.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We use as plug-in denoiser the Gradient-Step Denoiser (GSPnP) which provides an explicit prior.">

.. only:: html

  .. image:: /auto_examples/plug-and-play/images/thumb/sphx_glr_demo_RED_GSPnP_SR_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_plug-and-play_demo_RED_GSPnP_SR.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Regularization by Denoising (RED) for Super-Resolution.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to define your own optimization algorithm. For example, here, we implement the Condat-Vu Primal-Dual algorithm, and apply it for Single Pixel Camera reconstruction.">

.. only:: html

  .. image:: /auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_custom_optim_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_plug-and-play_demo_PnP_custom_optim.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">PnP with custom optimization algorithm (Condat-Vu Primal-Dual)</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Sampling
-------------------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This code shows you how to use sampling algorithms to quantify uncertainty of a reconstruction from incomplete and noisy measurements.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_sampling_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_sampling.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Uncertainty quantification with PnP-ULA.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This code shows you how to use the DDRM diffusion algorithm to reconstruct images and also compute the uncertainty of a reconstruction from incomplete and noisy measurements.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_ddrm_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_ddrm.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image reconstruction with a diffusion model</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This code shows how to build your custom sampling kernel. Here we build a preconditioned Unadjusted Langevin Algorithm (PreconULA) that takes advantage of the singular value decomposition of the forward operator to accelerate the sampling.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_custom_kernel_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_custom_kernel.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Building your custom sampling algorithm.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this tutorial, we will go over the steps in the Diffusion Posterior Sampling (DPS) algorithm introduced in Chung et al. The full algorithm is implemented in deepinv.sampling.DPS.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_dps_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_dps.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Implementing DPS</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This demo shows you how to use deepinv.sampling.PosteriorDiffusion to perform posterior sampling. It also can be used to perform unconditional image generation with arbitrary denoisers, if the data fidelity term is not specified.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_diffusion_sde_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_diffusion_sde.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Posterior Sampling for Inverse Problems with Stochastic Differential Equations modeling.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this tutorial, we revisit the implementation of the DiffPIR diffusion algorithm for image reconstruction from Zhou et al.. The full algorithm is implemented in deepinv.sampling.DiffPIR.">

.. only:: html

  .. image:: /auto_examples/sampling/images/thumb/sphx_glr_demo_diffpir_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_sampling_demo_diffpir.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Implementing DiffPIR</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Unfolded
-------------------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to implement the LISTA algorithm for a compressed sensing problem. In a nutshell, LISTA is an unfolded proximal gradient algorithm involving a soft-thresholding proximal operator with learnable thresholding parameters.">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_LISTA_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_LISTA.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Learned Iterative Soft-Thresholding Algorithm (LISTA) for compressed sensing</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This is a simple example to show how to use vanilla unfolded Plug-and-Play. The DnCNN denoiser and the algorithm parameters (stepsize, regularization parameters) are trained jointly. For simplicity, we show how to train the algorithm on a  small dataset. For optimal results, use a larger dataset. For visualizing the training, you can use Weight&amp;Bias (wandb) by setting wandb_vis=True.">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_vanilla_unfolded_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_vanilla_unfolded.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Vanilla Unfolded algorithm for super-resolution</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows how to implement a learned unrolled proximal gradient descent algorithm with a custom prior function. The algorithm is trained on a dataset of compressed sensing measurements of MNIST images.">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_custom_prior_unfolded_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_custom_prior_unfolded.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Learned iterative custom prior</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This a toy example to show you how to use DEQ to solve a deblurring problem. Note that this is a small dataset for training. For optimal results, use a larger dataset. For visualizing the training, you can use Weight&amp;Bias (wandb) by setting wandb_vis=True.">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_DEQ_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_DEQ.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Deep Equilibrium (DEQ) algorithms for image deblurring</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Adler, Jonas, and Ozan Öktem. &quot;Learned primal-dual reconstruction.&quot; IEEE transactions on medical imaging 37.6 (2018): 1322-1332.">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_learned_primal_dual_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_learned_primal_dual.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Learned Primal-Dual algorithm for CT scan.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Image inpainting consists in solving y = Ax where A is a mask operator. This problem can be reformulated as the following minimization problem:">

.. only:: html

  .. image:: /auto_examples/unfolded/images/thumb/sphx_glr_demo_unfolded_constrained_LISTA_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_unfolded_demo_unfolded_constrained_LISTA.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Unfolded Chambolle-Pock for constrained image inpainting</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Patch Priors
-------------------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example we use the expected patch log likelihood (EPLL) prior EPLL proposed in &quot;From learning models of natural image patches to whole image restoration&quot;. for denoising and inpainting of natural images. To this end, we consider the inverse problem y = Ax+\epsilon, where A is either the identity (for denoising) or a masking operator (for inpainting) and \epsilon\sim\mathcal{N}(0,\sigma^2 I) is white Gaussian noise with standard deviation \sigma.">

.. only:: html

  .. image:: /auto_examples/patch-priors/images/thumb/sphx_glr_demo_epll_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_patch-priors_demo_epll.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Expected Patch Log Likelihood (EPLL) for Denoising and Inpainting</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example we use patch priors for limited angle computed tomography. More precisely, we consider the inverse problem y = \mathrm{noisy}(Ax), where A is the discretized Radon transform with 100 equispace angles between 20 and 160 degrees. For the reconstruction, we minimize the variational problem">

.. only:: html

  .. image:: /auto_examples/patch-priors/images/thumb/sphx_glr_demo_patch_priors_CT_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_patch-priors_demo_patch_priors_CT.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Patch priors for limited-angle computed tomography</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Self-Supervised Learning
-------------------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example demonstrates various geometric image transformations implemented in deepinv that can be used in Equivariant Imaging (EI) for self-supervised learning:">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_ei_transforms_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_ei_transforms.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Image transformations for Equivariant Imaging</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We demonstrate self-supervised learning with measurement splitting, to train a denoiser network on the MNIST dataset. The physics here is noisy computed tomography, as is the case in Noise2Inverse. Note this example can also be easily applied to undersampled multicoil MRI as is the case in SSDU.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_splitting_loss_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_splitting_loss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised learning with measurement splitting</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a denoiser network in a fully self-supervised way, i.e., using noisy images with unknown noise level only via the UNSURE loss, which is introduced in https://arxiv.org/abs/2409.01985.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_unsure_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_unsure.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the UNSURE loss.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a denoiser network in a fully self-supervised way, i.e., using noisy images only via the SURE loss, which exploits knowledge about the noise distribution.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_sure_denoising_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_sure_denoising.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the SURE loss.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a denoiser network in a fully self-supervised way, i.e., using noisy images only via the Neighbor2Neighbor loss, which exploits the local correlation of natural images.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_n2n_denoising_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_n2n_denoising.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the Neighbor2Neighbor loss.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a reconstruction network for an MRI inverse problem on a fully self-supervised way, i.e., using measurement data only.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_equivariant_imaging_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_equivariant_imaging.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised learning with Equivariant Imaging for MRI.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a denoiser network in a fully self-supervised way, using noisy images only via the Generalized Recorrupted2Recorrupted (GR2R) loss, which exploits knowledge about the noise distribution. You can change the noise distribution by selecting from predefined noise models such as Gaussian, Poisson, and Gamma noise.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_r2r_denoising_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_r2r_denoising.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the Generalized R2R loss.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train a reconstruction network for an inpainting inverse problem on a fully self-supervised way, i.e., using measurement data only.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_multioperator_imaging_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_multioperator_imaging.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised learning from incomplete measurements of multiple operators.</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We demonstrate the self-supervised Artifact2Artifact loss for solving an undersampled sequential MRI reconstruction problem without ground truth.">

.. only:: html

  .. image:: /auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_artifact2artifact_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_self-supervised-learning_demo_artifact2artifact.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Self-supervised MRI reconstruction with Artifact2Artifact</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Adversarial Learning
--------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example shows you how to train various networks using adversarial training for deblurring problems. We demonstrate running training and inference using a conditional GAN (i.e. DeblurGAN), CSGM, AmbientGAN and UAIR implemented in the library, and how to simply train your own GAN by using deepinv.training.AdversarialTrainer. These examples can also be easily extended to train more complicated GANs such as CycleGAN.">

.. only:: html

  .. image:: /auto_examples/adversarial-learning/images/thumb/sphx_glr_demo_gan_imaging_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_adversarial-learning_demo_gan_imaging.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Imaging inverse problems with adversarial networks</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>

Advanced
-------------------------------




.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this example, we investigate a simple 2D Radio Interferometry (RI) imaging task with deepinverse. The following example and data are taken from Aghabiglou et al. (2024). If you are interested in RI imaging problem and would like to see more examples or try the state-of-the-art algorithms, please check BASPLib.">

.. only:: html

  .. image:: /auto_examples/advanced/images/thumb/sphx_glr_demo_ri_basic_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_advanced_demo_ri_basic.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Radio interferometric imaging with deepinverse</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:
   :includehidden:


   /auto_examples/basics/index.rst
   /auto_examples/optimization/index.rst
   /auto_examples/plug-and-play/index.rst
   /auto_examples/sampling/index.rst
   /auto_examples/unfolded/index.rst
   /auto_examples/patch-priors/index.rst
   /auto_examples/self-supervised-learning/index.rst
   /auto_examples/adversarial-learning/index.rst
   /auto_examples/advanced/index.rst


.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-gallery

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download all examples in Python source code: auto_examples_python.zip </auto_examples/auto_examples_python.zip>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download all examples in Jupyter notebooks: auto_examples_jupyter.zip </auto_examples/auto_examples_jupyter.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_