# Denoiser

### *class* deepinv.models.Denoiser(device='cpu')

Bases: [`Module`](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module)

Base class for denoiser models.

Provides a template for defining denoiser models.

While most denoisers $\denoisername$ are designed to handle Gaussian noise
with variance $\sigma^2$, this is not mandatory.

#### NOTE
A Denoiser can be converted into a [`Reconstructor`](https://deepinv.org/api/stubs/deepinv.models.Reconstructor.html.md#deepinv.models.Reconstructor)
by using the [`deepinv.models.ArtifactRemoval`](https://deepinv.org/api/stubs/deepinv.models.ArtifactRemoval.html.md#deepinv.models.ArtifactRemoval) class.

The base class inherits from [`torch.nn.Module`](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module).

#### forward(x, sigma, \*\*kwargs)

Applies denoiser $\denoiser{x}{\sigma}$.
The input `x` is expected to be with pixel values in `[0, 1]` range, up to random noise. The output is also expected to be in `[0, 1]` range.

* **Parameters:**
  * **x** ([*torch.Tensor*](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor)) – noisy input, of shape `[B, C, H, W]`.
  * **sigma** ([*torch.Tensor*](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor) *,* [*float*](https://docs.python.org/3.12/library/functions.html#float)) – noise level. Can be a `float` or a [`torch.Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor) of shape `[B]`.
    If a single `float` is provided, the same noise level is used for all samples in the batch.
    Otherwise, batch-wise noise levels are used.
* **Returns:**
  ([`torch.Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor)) Denoised tensor.
* **Return type:**
  [*Tensor*](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor)

<a id="sphx-glr-backref-deepinv-models-denoiser"></a>

## Examples using `Denoiser`:

<div class="sphx-glr-thumbnails">
<!-- thumbnail-parent-div-open --><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.">![](auto_examples/adversarial-learning/images/thumb/sphx_glr_demo_gan_imaging_thumb.png)

[Imaging inverse problems with adversarial networks](https://deepinv.org/auto_examples/adversarial-learning/demo_gan_imaging.html.md)

  <div class="sphx-glr-thumbnail-title">Imaging inverse problems with adversarial networks</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use DeepInverse with your own dataset.">![](auto_examples/basics/images/thumb/sphx_glr_demo_custom_dataset_thumb.png)

[Bring your own dataset](https://deepinv.org/auto_examples/basics/demo_custom_dataset.html.md)

  <div class="sphx-glr-thumbnail-title">Bring your own dataset</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Follow this example to reconstruct images using an iterative algorithm.">![](auto_examples/basics/images/thumb/sphx_glr_demo_custom_optim_thumb.png)

[Use iterative reconstruction algorithms](https://deepinv.org/auto_examples/basics/demo_custom_optim.html.md)

  <div class="sphx-glr-thumbnail-title">Use iterative reconstruction algorithms</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Follow this example to reconstruct images using a pretrained model in one line.">![](auto_examples/basics/images/thumb/sphx_glr_demo_pretrained_model_thumb.png)

[Use a pretrained model](https://deepinv.org/auto_examples/basics/demo_pretrained_model.html.md)

  <div class="sphx-glr-thumbnail-title">Use a pretrained model</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Follow this example to get started with DeepInverse in under 5 minutes.">![](auto_examples/basics/images/thumb/sphx_glr_demo_quickstart_thumb.png)

[5 minute quickstart tutorial](https://deepinv.org/auto_examples/basics/demo_quickstart.html.md)

  <div class="sphx-glr-thumbnail-title">5 minute quickstart tutorial</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example demonstrates blind image deblurring using the pretrained kernel estimation network from the paper carbajal2023blind. The network estimates spatially-varying blur kernels from a blurred image, which are then used in a space-varying blur physics model to reconstruct the sharp image using a non-blind deblurring algorithm.">![](auto_examples/blind-inverse-problems/images/thumb/sphx_glr_demo_blind_deblurring_thumb.png)

[Blind deblurring with kernel estimation network](https://deepinv.org/auto_examples/blind-inverse-problems/demo_blind_deblurring.html.md)

  <div class="sphx-glr-thumbnail-title">Blind deblurring with kernel estimation network</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example focuses on blind image Gaussian denoising, i.e. the problem">![](auto_examples/blind-inverse-problems/images/thumb/sphx_glr_demo_blind_denoising_thumb.png)

[Blind denoising with noise level estimation](https://deepinv.org/auto_examples/blind-inverse-problems/demo_blind_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">Blind denoising with noise level estimation</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In many imaging problems, the data to be processed can be very large, making it challenging to fit the denoising process into the memory of a single device. For instance, medical imaging or satellite imagery often involves processing gigapixel images that cannot be processed as a whole.">![](auto_examples/distributed/images/thumb/sphx_glr_demo_denoiser_distributed_thumb.png)

[Distributed Denoiser with Image Tiling](https://deepinv.org/auto_examples/distributed/demo_denoiser_distributed.html.md)

  <div class="sphx-glr-thumbnail-title">Distributed Denoiser with Image Tiling</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Many large-scale imaging problems involve operators that can be naturally decomposed as a stack of multiple sub-operators:">![](auto_examples/distributed/images/thumb/sphx_glr_demo_pnp_distributed_thumb.png)

[Distributed Plug-and-Play (PnP) Reconstruction](https://deepinv.org/auto_examples/distributed/demo_pnp_distributed.html.md)

  <div class="sphx-glr-thumbnail-title">Distributed Plug-and-Play (PnP) Reconstruction</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In many large-scale imaging problems, the size of the image/volume to reconstruct is very large, making it impossible to train reconstruction networks (in this example, unfolded networks) with a single GPU. The deepinv.distributed framework enables training a model on multiple GPUs, by carefully parallelizing the data fidelity and denoising steps inside the network.">![](auto_examples/distributed/images/thumb/sphx_glr_demo_unrolled_distributed_thumb.png)

[Distributed Training of Unfolded Networks](https://deepinv.org/auto_examples/distributed/demo_unrolled_distributed.html.md)

  <div class="sphx-glr-thumbnail-title">Distributed Training of Unfolded Networks</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="The data is taken from the 2DeteCT benchmark kiss2025benchmarking and dataset kiss20232detect, which is an industrial CT dataset of various materials acquired using a proprietary scanner from CWI (i.e. sinogram-to-image). The setup is matched exactly to kiss2025benchmarking, such that you can compare DeepInverse image reconstruction methods with the values reported in kiss2025benchmarking.">![](auto_examples/external-libraries/images/thumb/sphx_glr_demo_astra_2detect_thumb.png)

[Reconstruct real CT sinograms with the 2DeteCT benchmark](https://deepinv.org/auto_examples/external-libraries/demo_astra_2detect.html.md)

  <div class="sphx-glr-thumbnail-title">Reconstruct real CT sinograms with the 2DeteCT benchmark</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use Spyrit linear models and measurements with DeepInverse. Here we use the HadamSplit2d linear model from Spyrit.">![](auto_examples/external-libraries/images/thumb/sphx_glr_demo_connect_spyrit_thumb.png)

[Single-pixel imaging with Spyrit](https://deepinv.org/auto_examples/external-libraries/demo_connect_spyrit.html.md)

  <div class="sphx-glr-thumbnail-title">Single-pixel imaging with Spyrit</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to denoise low-intensity STED fluorescence microscopy images of live-cell mitochondria using the pretrained foundation model deepinv.models.RAM. We load real Abberior STED microscopy data from osunavargas2025denoising, process it in batches, and visualize the results both with deepinv.utils.plot and with the interactive 3D viewer deepinv.utils.plot_napari.">![](auto_examples/external-libraries/images/thumb/sphx_glr_demo_microscopy_denoising_thumb.png)

[Low-intensity STED fluorescence microscopy denoising](https://deepinv.org/auto_examples/external-libraries/demo_microscopy_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">Low-intensity STED fluorescence microscopy denoising</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to fit deepinv.loss.metric.NIQE on a new dataset, and use it to evaluate denoiser performance.">![](auto_examples/metrics/images/thumb/sphx_glr_demo_custom_niqe_thumb.png)

[Fitting NIQE on a custom dataset](https://deepinv.org/auto_examples/metrics/demo_custom_niqe.html.md)

  <div class="sphx-glr-thumbnail-title">Fitting NIQE on a custom dataset</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In blind inverse problems, some parameters of the physics are unknown at test time. Running non-blind models requires knowing these parameters, which are often hard to estimate. For example, a denoiser needs the noise level \\sigma, a deblurring model needs the blur kernel.">![](auto_examples/metrics/images/thumb/sphx_glr_demo_test_time_tuning_thumb.png)

[Blind inverse problems with no reference metrics](https://deepinv.org/auto_examples/metrics/demo_test_time_tuning.html.md)

  <div class="sphx-glr-thumbnail-title">Blind inverse problems with no reference metrics</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example provides a tour of the denoisers in DeepInverse. A denoiser is a model that takes in a noisy image and outputs a denoised version of it. Basically, it solves the following problem:">![](auto_examples/models/images/thumb/sphx_glr_demo_denoiser_tour_thumb.png)

[Benchmarking pretrained denoisers](https://deepinv.org/auto_examples/models/demo_denoiser_tour.html.md)

  <div class="sphx-glr-thumbnail-title">Benchmarking pretrained denoisers</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to perform inference on and fine-tune the Reconstruct Anything Model (RAM) foundation model terris2025reconstruct to solve inverse problems.">![](auto_examples/models/images/thumb/sphx_glr_demo_foundation_model_thumb.png)

[Inference and fine-tune a foundation model](https://deepinv.org/auto_examples/models/demo_foundation_model.html.md)

  <div class="sphx-glr-thumbnail-title">Inference and fine-tune a foundation model</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This demo reconstructs undersampled k-space data for 2D cardiac and brain MRI on:">![](auto_examples/models/images/thumb/sphx_glr_demo_mri_pretrained_thumb.png)

[Reconstruct undersampled k-space for cardiac and brain MRI](https://deepinv.org/auto_examples/models/demo_mri_pretrained.html.md)

  <div class="sphx-glr-thumbnail-title">Reconstruct undersampled k-space for cardiac and brain MRI</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example reconstructs real prospectively undersampled multicoil brain k-space from yu2022validation.">![](auto_examples/models/images/thumb/sphx_glr_demo_prospective_mri_thumb.png)

[Reconstruct prospectively-undersampled raw multicoil MRI](https://deepinv.org/auto_examples/models/demo_prospective_mri.html.md)

  <div class="sphx-glr-thumbnail-title">Reconstruct prospectively-undersampled raw multicoil MRI</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example provides a very simple quick start introduction to training reconstruction networks with DeepInverse for solving imaging inverse problems.">![](auto_examples/models/images/thumb/sphx_glr_demo_training_thumb.png)

[Training a reconstruction model](https://deepinv.org/auto_examples/models/demo_training.html.md)

  <div class="sphx-glr-thumbnail-title">Training a reconstruction model</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use variational 3D denoisers for denoising a 3D image. We first apply a standard soft-thresholding wavelet denoiser to a 3D brain MRI volume, as well as a 3D TV denoiser. We then extend the wavelet 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.">![](auto_examples/optimization/images/thumb/sphx_glr_demo_3D_denoising_thumb.png)

[3D denoising of brain MRI with wavelet and TV priors](https://deepinv.org/auto_examples/optimization/demo_3D_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">3D denoising of brain MRI with wavelet and TV priors</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example demonstrates how to denoise images corrupted by Poisson-Gaussian noise using the Generalized Anscombe Transform (GAT), which converts any Gaussian denoiser into a Poisson-Gaussian denoiser makitalo2012optimal.">![](auto_examples/physics/images/thumb/sphx_glr_demo_anscombe_thumb.png)

[Poisson-Gaussian Denoising with the Generalized Anscombe Transform](https://deepinv.org/auto_examples/physics/demo_anscombe.html.md)

  <div class="sphx-glr-thumbnail-title">Poisson-Gaussian Denoising with the Generalized Anscombe Transform</div>
</div><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:">![](auto_examples/physics/images/thumb/sphx_glr_demo_mri_tour_thumb.png)

[Tour of MRI functionality in DeepInverse](https://deepinv.org/auto_examples/physics/demo_mri_tour.html.md)

  <div class="sphx-glr-thumbnail-title">Tour of MRI functionality in DeepInverse</div>
</div><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:">![](auto_examples/physics/images/thumb/sphx_glr_demo_phase_retrieval_thumb.png)

[Random phase retrieval and reconstruction methods.](https://deepinv.org/auto_examples/physics/demo_phase_retrieval.html.md)

  <div class="sphx-glr-thumbnail-title">Random phase retrieval and reconstruction methods.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This demo illustrates the impact of different Hadamard pattern ordering algorithms in the Single Pixel Camera (SPC), a computational imaging system that uses a single photodetector to capture images by projecting the scene onto a series of patterns. The SPC is implemented in the DeepInverse library.">![](auto_examples/physics/images/thumb/sphx_glr_demo_spc_thumb.png)

[Pattern Ordering in a Compressive Single Pixel Camera](https://deepinv.org/auto_examples/physics/demo_spc.html.md)

  <div class="sphx-glr-thumbnail-title">Pattern Ordering in a Compressive Single Pixel Camera</div>
</div><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 zhang2021plug. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3929-3938).">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_DPIR_deblur_thumb.png)

[DPIR method for PnP image deblurring.](https://deepinv.org/auto_examples/plug-and-play/demo_PnP_DPIR_deblur.html.md)

  <div class="sphx-glr-thumbnail-title">DPIR method for PnP image deblurring.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to define your own optimization algorithm. For example, here, we implement the Primal-Dual Condat-Vu (CV) algorithm, and apply it for Single Pixel Camera reconstruction.">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_custom_optim_thumb.png)

[PnP with custom optimization algorithm (Primal-Dual Condat-Vu)](https://deepinv.org/auto_examples/plug-and-play/demo_PnP_custom_optim.html.md)

  <div class="sphx-glr-thumbnail-title">PnP with custom optimization algorithm (Primal-Dual Condat-Vu)</div>
</div><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. See hurault2023convergent for more details.">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_mirror_descent_thumb.png)

[Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.](https://deepinv.org/auto_examples/plug-and-play/demo_PnP_mirror_descent.html.md)

  <div class="sphx-glr-thumbnail-title">Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Plug-and-Play (PnP) is known to be challenging to apply to certain inverse problems like inpainting. One way to overcome this is to use a multi-scale approach instead of the standard single-scale approach.">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_PnP_multiscale_thumb.png)

[Multi-scale Plug-and-Play for Inpainting](https://deepinv.org/auto_examples/plug-and-play/demo_PnP_multiscale.html.md)

  <div class="sphx-glr-thumbnail-title">Multi-scale Plug-and-Play for Inpainting</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use deepinv.physics.UltrasoundPlaneWave to reconstructs an in-vivo carotid acquisition of the EPFL LTS5 ultrafast ultrasound dataset from raw RF ultrasound data.">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_ultrasound_invivo_PnP_thumb.png)

[In-vivo ultrafast ultrasound reconstruction with Plug-and-Play](https://deepinv.org/auto_examples/plug-and-play/demo_ultrasound_invivo_PnP.html.md)

  <div class="sphx-glr-thumbnail-title">In-vivo ultrafast ultrasound reconstruction with Plug-and-Play</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example shows how to use a standard PnP algorithm with DnCNN denoiser for computed tomography.">![](auto_examples/plug-and-play/images/thumb/sphx_glr_demo_vanilla_PnP_thumb.png)

[Vanilla PnP for computed tomography (CT).](https://deepinv.org/auto_examples/plug-and-play/demo_vanilla_PnP.html.md)

  <div class="sphx-glr-thumbnail-title">Vanilla PnP for computed tomography (CT).</div>
</div><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.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_custom_kernel_thumb.png)

[Building your custom MCMC sampling algorithm.](https://deepinv.org/auto_examples/sampling/demo_custom_kernel.html.md)

  <div class="sphx-glr-thumbnail-title">Building your custom MCMC sampling algorithm.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This code shows you how to use the DDRM diffusion algorithm kawar2022denoising to reconstruct images and also compute the uncertainty of a reconstruction from incomplete and noisy measurements.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_ddrm_thumb.png)

[Image reconstruction with a diffusion model](https://deepinv.org/auto_examples/sampling/demo_ddrm.html.md)

  <div class="sphx-glr-thumbnail-title">Image reconstruction with a diffusion model</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In this tutorial, we revisit the implementation of the DiffPIR diffusion algorithm for image reconstruction from zhu2023denoising. The full algorithm is implemented in deepinv.sampling.DiffPIR.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_diffpir_thumb.png)

[Implementing DiffPIR](https://deepinv.org/auto_examples/sampling/demo_diffpir.html.md)

  <div class="sphx-glr-thumbnail-title">Implementing DiffPIR</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This demo shows you how to use our wrapper deepinv.models.DiffusersDenoiserWrapper to turn any SOTA models from the HuggingFace Hub to an image denoiser. It also can be used to perform unconditional image generation or for posterior sampling.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_diffusers_thumb.png)

[Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse](https://deepinv.org/auto_examples/sampling/demo_diffusers.html.md)

  <div class="sphx-glr-thumbnail-title">Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse</div>
</div><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.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_diffusion_sde_thumb.png)

[Building your diffusion posterior sampling method using SDEs](https://deepinv.org/auto_examples/sampling/demo_diffusion_sde.html.md)

  <div class="sphx-glr-thumbnail-title">Building your diffusion posterior sampling method using SDEs</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In this tutorial, we will go over the steps in the Diffusion Posterior Sampling (DPS) algorithm introduced in chung2022diffusion. The full algorithm is implemented in deepinv.sampling.DPS.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_dps_thumb.png)

[DPS – Posterior Sampling with Diffusion Models](https://deepinv.org/auto_examples/sampling/demo_dps.html.md)

  <div class="sphx-glr-thumbnail-title">DPS -- Posterior Sampling with Diffusion Models</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This demo shows you how to perform unconditional image generation and posterior sampling using Flow Matching (FM).">![](auto_examples/sampling/images/thumb/sphx_glr_demo_flow_matching_thumb.png)

[Flow-Matching for posterior sampling and unconditional generation](https://deepinv.org/auto_examples/sampling/demo_flow_matching.html.md)

  <div class="sphx-glr-thumbnail-title">Flow-Matching for posterior sampling and unconditional generation</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example compares six approximations of the measurement-matching term used by diffusion posterior samplers.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_noisy_data_fidelity_thumb.png)

[Noisy data-fidelity terms for diffusion posterior sampling](https://deepinv.org/auto_examples/sampling/demo_noisy_data_fidelity.html.md)

  <div class="sphx-glr-thumbnail-title">Noisy data-fidelity terms for diffusion posterior sampling</div>
</div><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.">![](auto_examples/sampling/images/thumb/sphx_glr_demo_sampling_thumb.png)

[Uncertainty quantification with PnP-ULA.](https://deepinv.org/auto_examples/sampling/demo_sampling.html.md)

  <div class="sphx-glr-thumbnail-title">Uncertainty quantification with PnP-ULA.</div>
</div><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:">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_ei_transforms_thumb.png)

[Image transformations for Equivariant Imaging](https://deepinv.org/auto_examples/self-supervised-learning/demo_ei_transforms.html.md)

  <div class="sphx-glr-thumbnail-title">Image transformations for Equivariant Imaging</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Equivariant splitting consists in minimizing a self-supervised loss to train a reconstruction model using measurement data only sechaud26Equivariant.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_equivariant_splitting_thumb.png)

[Self-supervised learning with Equivariant Splitting](https://deepinv.org/auto_examples/self-supervised-learning/demo_equivariant_splitting.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised learning with Equivariant Splitting</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="We demonstrate self-supervised (blind) denoising of a low-field MRI scan without ground truth data.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_lowfieldmri_thumb.png)

[Low-field MRI denoising without ground truth](https://deepinv.org/auto_examples/self-supervised-learning/demo_lowfieldmri.html.md)

  <div class="sphx-glr-thumbnail-title">Low-field MRI denoising without ground truth</div>
</div><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.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_multioperator_imaging_thumb.png)

[Self-supervised learning from incomplete measurements of multiple operators.](https://deepinv.org/auto_examples/self-supervised-learning/demo_multioperator_imaging.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised learning from incomplete measurements of multiple operators.</div>
</div><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.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_n2n_denoising_thumb.png)

[Self-supervised denoising with the Neighbor2Neighbor loss.](https://deepinv.org/auto_examples/self-supervised-learning/demo_n2n_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the Neighbor2Neighbor loss.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This code shows how to restore a single image corrupted by Poisson noise using Poisson2Sparse, without requiring external training or knowledge of the noise level.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_poisson2sparse_thumb.png)

[Poisson denoising using Poisson2Sparse](https://deepinv.org/auto_examples/self-supervised-learning/demo_poisson2sparse.html.md)

  <div class="sphx-glr-thumbnail-title">Poisson denoising using Poisson2Sparse</div>
</div><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 monroy2025generalized, 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.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_r2r_denoising_thumb.png)

[Self-supervised denoising with the Generalized R2R loss.](https://deepinv.org/auto_examples/self-supervised-learning/demo_r2r_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the Generalized R2R loss.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="We demonstrate scan-specific self-supervised learning, that is, learning to reconstruct MRI scans from a single accelerated sample without ground truth.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_scan_specific_thumb.png)

[Scan-specific zero-shot SSDU for MRI](https://deepinv.org/auto_examples/self-supervised-learning/demo_scan_specific.html.md)

  <div class="sphx-glr-thumbnail-title">Scan-specific zero-shot SSDU for MRI</div>
</div><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 hendriksen2020noise2inverse. Note this example can also be easily applied to undersampled multicoil MRI as is the case in SSDU yaman2020self.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_splitting_loss_thumb.png)

[Self-supervised learning with measurement splitting](https://deepinv.org/auto_examples/self-supervised-learning/demo_splitting_loss.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised learning with measurement splitting</div>
</div><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.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_sure_denoising_thumb.png)

[Self-supervised denoising with the SURE loss.](https://deepinv.org/auto_examples/self-supervised-learning/demo_sure_denoising.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the SURE loss.</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example despeckles real clinical ultrasound B-mode images with Speckle2Self li2025speckle2self, a model pretrained without clean reference images.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_ultrasound_despeckling_thumb.png)

[Ultrasound despeckling from B-mode images](https://deepinv.org/auto_examples/self-supervised-learning/demo_ultrasound_despeckling.html.md)

  <div class="sphx-glr-thumbnail-title">Ultrasound despeckling from B-mode images</div>
</div><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 by tachella2024unsure.">![](auto_examples/self-supervised-learning/images/thumb/sphx_glr_demo_unsure_thumb.png)

[Self-supervised denoising with the UNSURE loss.](https://deepinv.org/auto_examples/self-supervised-learning/demo_unsure.html.md)

  <div class="sphx-glr-thumbnail-title">Self-supervised denoising with the UNSURE loss.</div>
</div><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:">![](auto_examples/transforms-equivariance/images/thumb/sphx_glr_demo_transforms_thumb.png)

[Image transforms for equivariance & augmentations](https://deepinv.org/auto_examples/transforms-equivariance/demo_transforms.html.md)

  <div class="sphx-glr-thumbnail-title">Image transforms for equivariance & augmentations</div>
</div><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.">![](auto_examples/unfolded/images/thumb/sphx_glr_demo_DEQ_thumb.png)

[Deep Equilibrium (DEQ) algorithms for image deblurring](https://deepinv.org/auto_examples/unfolded/demo_DEQ.html.md)

  <div class="sphx-glr-thumbnail-title">Deep Equilibrium (DEQ) algorithms for image deblurring</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="Some unfolded architectures rely on a least-squares solver to compute the proximal step w.r.t. the data-fidelity term (e.g., ADMM or HQS):  ">![](auto_examples/unfolded/images/thumb/sphx_glr_demo_unfolded_constant_memory_thumb.png)

[Reducing the memory and computational complexity of unfolded network training](https://deepinv.org/auto_examples/unfolded/demo_unfolded_constant_memory.html.md)

  <div class="sphx-glr-thumbnail-title">Reducing the memory and computational complexity of unfolded network training</div>
</div><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:">![](auto_examples/unfolded/images/thumb/sphx_glr_demo_unfolded_constrained_LISTA_thumb.png)

[Unfolded Chambolle-Pock for constrained image inpainting](https://deepinv.org/auto_examples/unfolded/demo_unfolded_constrained_LISTA.html.md)

  <div class="sphx-glr-thumbnail-title">Unfolded Chambolle-Pock for constrained image inpainting</div>
</div><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.">![](auto_examples/unfolded/images/thumb/sphx_glr_demo_vanilla_unfolded_thumb.png)

[Vanilla Unfolded algorithm for super-resolution](https://deepinv.org/auto_examples/unfolded/demo_vanilla_unfolded.html.md)

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