deepinv

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.1%) to scientific vocabulary

Keywords

computational-imaging computed-tomography deblurring deep-equilibrium-models deep-learning diffusion-models image-processing image-reconstruction imaging inverse-problems mri plug-and-play super-resolution unfolded

Last synced: 6 months ago · JSON representation ·

Repository

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

Basic Info

Host: GitHub
Owner: deepinv
License: bsd-3-clause
Language: Python
Default Branch: main
Homepage: https://deepinv.github.io
Size: 216 MB

Statistics

Stars: 501
Watchers: 8
Forks: 107
Open Issues: 76
Releases: 10

Topics

Created about 3 years ago · Last pushed 6 months ago

Metadata Files

Readme Changelog Contributing License Code of conduct Citation Security Maintainers

README.rst

.. image:: https://github.com/deepinv/deepinv/raw/main/docs/source/figures/deepinv_logolarge.png
:width: 500px
:alt: deepinv logo
:align: center

Introduction
------------
`DeepInverse `_ is an open-source PyTorch-based library for solving imaging inverse problems with deep learning. ``deepinv`` accelerates deep learning research across imaging domains, enhances research reproducibility via a common modular framework of problems and algorithms, and lowers the entrance bar to new practitioners.

.. image:: https://github.com/deepinv/deepinv/raw/main/docs/source/figures/deepinv_schematic.png
:width: 1000px
:alt: deepinv schematic
:align: center

Get started
-----------

Read our **documentation** at `deepinv.github.io `_. Check out our `5 minute quickstart tutorial `_, our `comprehensive examples `_, or our `User Guide `_.

``deepinv`` features

* A large framework of `predefined imaging operators `_
* Many `state-of-the-art deep neural networks `_, including pretrained out-of-the-box `reconstruction models `_ and `denoisers `_
* Comprehensive frameworks for `plug-and-play restoration `_, `optimization `_ and `unfolded architectures `_
* `Training losses `_ for inverse problems
* `Sampling algorithms and diffusion models `_ for uncertainty quantification
* A framework for `building datasets `_ for inverse problems

Install
-------

Install the latest stable release of ``deepinv``:

.. code-block:: bash

pip install deepinv

# Or:

uv pip install deepinv # faster

# Or, for additional dependencies:

pip install deepinv[dataset,denoisers]

Since ``deepinv`` is under active development, you can install the latest nightly version using:

.. code-block:: bash

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

# Or, for updating:

pip install --upgrade --force-reinstall --no-deps git+https://github.com/deepinv/deepinv.git#egg=deepinv

Contributing
------------

DeepInverse is a community-driven project and we encourage contributions of all forms.
We are building a comprehensive library of inverse problems and deep learning,
and we need your help to get there!

Interested? Check out our `contributing guide `_.

Finding help
------------

If you have any questions or suggestions, please join the conversation in our
`Discord server `_. The recommended way to get in touch with the developers about any bugs or issues is to
`open an issue `_.

Maintainers
-----------

Get in touch with our `MAINTAINERS `_.

Citation
--------
If you use DeepInverse in your research, please cite `our paper on arXiv `_:

.. code-block:: bash

@software{tachella2025deepinverse,
title={DeepInverse: A Python package for solving imaging inverse problems with deep learning},
author={Julián Tachella and Matthieu Terris and Samuel Hurault and Andrew Wang and Dongdong Chen and Minh-Hai Nguyen and Maxime Song and Thomas Davies and Leo Davy and Jonathan Dong and Paul Escande and Johannes Hertrich and Zhiyuan Hu and Tobías I. Liaudat and Nils Laurent and Brett Levac and Mathurin Massias and Thomas Moreau and Thibaut Modrzyk and Brayan Monroy and Sebastian Neumayer and Jérémy Scanvic and Florian Sarron and Victor Sechaud and Georg Schramm and Romain Vo and Pierre Weiss},
year={2025},
eprint={2505.20160},
archivePrefix={arXiv},
primaryClass={eess.IV},
url={https://arxiv.org/abs/2505.20160},
}

Star history
------------

.. image:: https://api.star-history.com/svg?repos=deepinv/deepinv&type=Date
:alt: Star History Chart
:target: https://www.star-history.com/#deepinv/deepinv&Date

.. |Black| image:: https://img.shields.io/badge/code%20style-black-000000.svg
:target: https://github.com/psf/black
.. |Test Status| image:: https://github.com/deepinv/deepinv/actions/workflows/test.yml/badge.svg
:target: https://github.com/deepinv/deepinv/actions/workflows/test.yml
.. |Docs Status| image:: https://github.com/deepinv/deepinv/actions/workflows/documentation.yml/badge.svg
:target: https://github.com/deepinv/deepinv/actions/workflows/documentation.yml
.. |Python Version| image:: https://img.shields.io/badge/python-3.10%2B-blue
:target: https://www.python.org/downloads/release/python-3100/
.. |codecov| image:: https://codecov.io/gh/deepinv/deepinv/branch/main/graph/badge.svg?token=77JRvUhQzh
:target: https://codecov.io/gh/deepinv/deepinv
.. |pip install| image:: https://img.shields.io/pypi/dm/deepinv.svg?logo=pypi&label=pip%20install&color=fedcba
:target: https://pypistats.org/packages/deepinv
.. |discord| image:: https://dcbadge.limes.pink/api/server/qBqY5jKw3p?style=flat
:target: https://discord.gg/qBqY5jKw3p
.. |colab| image:: https://colab.research.google.com/assets/colab-badge.svg
:target: https://colab.research.google.com/drive/11YKc_fq4VS70fL8mFzmWgWpZJ7iTE9tI?usp=sharing

Owner

Name: deepinv
Login: deepinv
Kind: organization

Website: deepinv.github.io
Repositories: 1
Profile: https://github.com/deepinv

JOSS Publication

DeepInverse: A Python package for solving imaging inverse problems with deep learning

Published

November 19, 2025

DOI

10.21105/joss.08923

Volume 10, Issue 115, Page 8923

Authors

Julián Tachella

CNRS, ENS de Lyon, France

Matthieu Terris
Université Paris-Saclay, Inria, CEA, Palaiseau, France

Samuel Hurault
CNRS, ENS Paris, PSL, France

Andrew Wang

University of Edinburgh, UK

Leo Davy
CNRS, ENS de Lyon, France

Jérémy Scanvic
CNRS, ENS de Lyon, France

Victor Sechaud
CNRS, ENS de Lyon, France

Romain Vo
CNRS, ENS de Lyon, France

Thomas Moreau
Université Paris-Saclay, Inria, CEA, Palaiseau, France

Thomas Davies
University of Edinburgh, UK, Heriot-Watt University, Edinburgh, UK

Dongdong Chen
Heriot-Watt University, Edinburgh, UK

Nils Laurent
Universidad Industrial de Santander, Bucaramanga, Colombia

Brayan Monroy
Universidad Industrial de Santander, Bucaramanga, Colombia

Jonathan Dong
EPFL, Lausanne, Switzerland

Zhiyuan Hu
EPFL, Lausanne, Switzerland

Minh-Hai Nguyen
IRIT, CBI, CNRS, Université de Toulouse, France

Florian Sarron
IRIT, CBI, CNRS, Université de Toulouse, France

Pierre Weiss
IRIT, CBI, CNRS, Université de Toulouse, France

Paul Escande
IMT, CNRS, Université de Toulouse, France

Mathurin Massias
Inria, ENS de Lyon, France

Thibaut Modrzyk
INSA de Lyon, France

Brett Levac
University of Texas at Austin, USA

Tobías I. Liaudat
IRFU, CEA, Université Paris-Saclay, Gif-sur-Yvette, France

Maxime Song
CNRS UAR 851, Université Paris-Saclay Orsay, France

Johannes Hertrich
Université Paris Dauphine - PSL, Paris, France

Sebastian Neumayer
Chemnitz University of Technology, Chemnitz, Germany

Georg Schramm

Department of Imaging and Pathology, KU Leuven, Belgium

Editor

Vissarion Fisikopoulos

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "DeepInverse: A Python package for solving imaging inverse problems with deep learning"
authors:
  - family-names: "Tachella"
    given-names: "Julián"
  - family-names: "Terris"
    given-names: "Matthieu"
  - family-names: "Hurault"
    given-names: "Samuel"
  - family-names: "Wang"
    given-names: "Andrew"
  - family-names: "Chen"
    given-names: "Dongdong"
  - family-names: "Nguyen"
    given-names: "Minh-Hai"
  - family-names: "Song"
    given-names: "Maxime"
  - family-names: "Davies"
    given-names: "Thomas"
  - family-names: "Davy"
    given-names: "Leo"
  - family-names: "Dong"
    given-names: "Jonathan"
  - family-names: "Escande"
    given-names: "Paul"
  - family-names: "Hertrich"
    given-names: "Johannes"
  - family-names: "Hu"
    given-names: "Zhiyuan"
  - family-names: "Liaudat"
    given-names: "Tobías I."
  - family-names: "Laurent"
    given-names: "Nils"
  - family-names: "Levac"
    given-names: "Brett"
  - family-names: "Massias"
    given-names: "Mathurin"
  - family-names: "Moreau"
    given-names: "Thomas"
  - family-names: "Modrzyk"
    given-names: "Thibaut"
  - family-names: "Monroy"
    given-names: "Brayan"
  - family-names: "Neumayer"
    given-names: "Sebastian"
  - family-names: "Scanvic"
    given-names: "Jérémy"
  - family-names: "Sarron"
    given-names: "Florian"
  - family-names: "Sechaud"
    given-names: "Victor"
  - family-names: "Schramm"
    given-names: "Georg"
  - family-names: "Vo"
    given-names: "Romain"
  - family-names: "Weiss"
    given-names: "Pierre"
doi: "https://doi.org/10.48550/arXiv.2505.20160"
date-released: 2023-06-30
repository-code: "https://github.com/deepinv/deepinv"
url: "https://arxiv.org/abs/2505.20160"
license: "BSD 3"
keywords:
  - "inverse problems"
  - "deep learning"
  - "imaging"
  - "Python"

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 163
Total pull requests: 309
Average time to close issues: 23 days
Average time to close pull requests: 14 days
Total issue authors: 45
Total pull request authors: 51
Average comments per issue: 0.82
Average comments per pull request: 0.92
Merged pull requests: 195
Bot issues: 0
Bot pull requests: 1

Past Year

Issues: 116
Pull requests: 199
Average time to close issues: 13 days
Average time to close pull requests: 11 days
Issue authors: 33
Pull request authors: 40
Average comments per issue: 0.59
Average comments per pull request: 0.88
Merged pull requests: 115
Bot issues: 0
Bot pull requests: 1

View more stats

Top Authors

Issue Authors

Andrewwango (35)
jscanvic (24)
matthieutrs (12)
tachella (12)
Tmodrzyk (9)
samuro95 (5)
gschramm (5)
mh-nguyen712 (5)
Nils-Laurent (4)
svvenkatakrishnan (3)
edongdongchen (3)
fedor-goncharov (3)
vsechaud (3)
mathurinm (2)
merminie (2)

Pull Request Authors

Andrewwango (62)
tachella (48)
jscanvic (39)
matthieutrs (24)
samuro95 (20)
MaximeSongIdris (15)
mh-nguyen712 (11)
tomMoral (8)
bemc22 (7)
Tmodrzyk (6)
vsechaud (5)
johertrich (5)
mathurinm (5)
Nils-Laurent (4)
eliottbourrigan (4)

Top Labels

Issue Labels

bug (26) documentation (11) enhancement (11) good first issue (7) help wanted (2) wontfix (2)

Pull Request Labels

bug (2) enhancement (2) documentation (1) good first issue (1)

Packages

Total packages: 1
Total downloads:
- pypi 1,650 last-month

Total dependent packages: 0
Total dependent repositories: 1
Total versions: 11
Total maintainers: 1

pypi.org: deepinv

DeepInverse: a PyTorch library for imaging with deep learning

Homepage: https://deepinv.github.io/
Documentation: https://deepinv.readthedocs.io/
License: BSD 3-Clause
Latest release: 0.3.3
published 7 months ago

Versions: 11
Dependent Packages: 0
Dependent Repositories: 1
Downloads: 1,650 Last month

Rankings

Dependent packages count: 10.1%

Average: 19.0%

Dependent repos count: 21.5%

Downloads: 25.4%

Maintainers (1)

tachellajulian

Last synced: 6 months ago

Dependencies

.github/workflows/documentation.yml actions

actions/checkout v3 composite
actions/setup-python v3 composite
peaceiris/actions-gh-pages v3 composite

environment.yml pypi

fastmri *

.github/workflows/lint.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
psf/black stable composite

.github/workflows/test.yml actions

actions/checkout v3 composite
actions/setup-python v3 composite
codecov/codecov-action v3 composite

pyproject.toml pypi

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science

deepinv

Science Score: 54.0%

Keywords

Repository

Basic Info

Statistics

Topics

Metadata Files

README.rst

Owner

JOSS Publication

DeepInverse: A Python package for solving imaging inverse problems with deep learning

Authors

Editor

Tags

Citation (CITATION.cff)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: deepinv

Rankings

Maintainers (1)

Dependencies