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

Julián Tachella; Matthieu Terris; Samuel Hurault; Andrew Wang; Leo Davy; Jérémy Scanvic; Victor Sechaud; Romain Vo; Thomas Moreau; Thomas Davies; Dongdong Chen; Nils Laurent; Brayan Monroy; Jonathan Dong; Zhiyuan Hu; Minh-Hai Nguyen; Florian Sarron; Pierre Weiss; Paul Escande; Mathurin Massias; Thibaut Modrzyk; Brett Levac; Tobías I. Liaudat; Maxime Song; Johannes Hertrich; Sebastian Neumayer; Georg Schramm

doi:10.21105/joss.08923

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

Julián Tachella
, Matthieu Terris
, Samuel Hurault
, Andrew Wang
, Leo Davy
, Jérémy Scanvic
, Victor Sechaud
, Romain Vo
, Thomas Moreau
, Thomas Davies
, Dongdong Chen
, Nils Laurent
, Brayan Monroy
, Jonathan Dong
, Zhiyuan Hu
, Minh-Hai Nguyen
, Florian Sarron
, Pierre Weiss
, Paul Escande
, Mathurin Massias

Thibaut Modrzyk, Brett Levac, Tobías I. Liaudat, Maxime Song, Johannes Hertrich, Sebastian Neumayer, Georg Schramm

Research output: Contribution to journal › Article › peer-review

3 Downloads (Pure)

Abstract

DeepInverse is an open-source PyTorch-based library for imaging inverse problems. DeepInverse implements all steps for image reconstruction, including efficient forward operators, defining and solving variational problems and designing and training advanced neural networks, for a wide set of domains (medical imaging, astronomical imaging, remote sensing, computational photography, compressed sensing and more).

Original language	English
Article number	8923
Journal	The Journal of Open Source Software
Volume	10
Issue number	115
DOIs	https://doi.org/10.21105/joss.08923
Publication status	Published - 19 Nov 2025

Access to Document

10.21105/joss.08923Licence: CC BY

Download pdf
Authors of papers retain copyright and release the work under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Final published version, 864 KBLicence: CC BY

Cite this

Tachella, J., Terris, M., Hurault, S., Wang, A., Davy, L., Scanvic, J., Sechaud, V., Vo, R., Moreau, T., Davies, T., Chen, D., Laurent, N., Monroy, B., Dong, J., Hu, Z., Nguyen, M.-H., Sarron, F., Weiss, P., Escande, P., ... Schramm, G. (2025). DeepInverse: A Python package for solving imaging inverse problems with deep learning. The Journal of Open Source Software, 10(115), Article 8923. https://doi.org/10.21105/joss.08923

@article{37b69c09f0f84d6eafb9ab58675f055f,

title = "DeepInverse: A Python package for solving imaging inverse problems with deep learning",

abstract = "DeepInverse is an open-source PyTorch-based library for imaging inverse problems. DeepInverse implements all steps for image reconstruction, including efficient forward operators, defining and solving variational problems and designing and training advanced neural networks, for a wide set of domains (medical imaging, astronomical imaging, remote sensing, computational photography, compressed sensing and more).",

author = "Juli{\'a}n Tachella and Matthieu Terris and Samuel Hurault and Andrew Wang and Leo Davy and J{\'e}r{\'e}my Scanvic and Victor Sechaud and Romain Vo and Thomas Moreau and Thomas Davies and Dongdong Chen and Nils Laurent and Brayan Monroy and Jonathan Dong and Zhiyuan Hu and Minh-Hai Nguyen and Florian Sarron and Pierre Weiss and Paul Escande and Mathurin Massias and Thibaut Modrzyk and Brett Levac and Liaudat, \{Tob{\'i}as I.\} and Maxime Song and Johannes Hertrich and Sebastian Neumayer and Georg Schramm",

year = "2025",

month = nov,

day = "19",

doi = "10.21105/joss.08923",

language = "English",

volume = "10",

journal = "The Journal of Open Source Software",

issn = "2475-9066",

publisher = "The Open Journal",

number = "115",

}

Tachella, J, Terris, M, Hurault, S, Wang, A, Davy, L, Scanvic, J, Sechaud, V, Vo, R, Moreau, T, Davies, T, Chen, D, Laurent, N, Monroy, B, Dong, J, Hu, Z, Nguyen, M-H, Sarron, F, Weiss, P, Escande, P, Massias, M, Modrzyk, T, Levac, B, Liaudat, TI, Song, M, Hertrich, J, Neumayer, S & Schramm, G 2025, 'DeepInverse: A Python package for solving imaging inverse problems with deep learning', The Journal of Open Source Software, vol. 10, no. 115, 8923. https://doi.org/10.21105/joss.08923

TY - JOUR

T1 - DeepInverse: A Python package for solving imaging inverse problems with deep learning

AU - Tachella, Julián

AU - Terris, Matthieu

AU - Hurault, Samuel

AU - Wang, Andrew

AU - Davy, Leo

AU - Scanvic, Jérémy

AU - Sechaud, Victor

AU - Vo, Romain

AU - Moreau, Thomas

AU - Davies, Thomas

AU - Chen, Dongdong

AU - Laurent, Nils

AU - Monroy, Brayan

AU - Dong, Jonathan

AU - Hu, Zhiyuan

AU - Nguyen, Minh-Hai

AU - Sarron, Florian

AU - Weiss, Pierre

AU - Escande, Paul

AU - Massias, Mathurin

AU - Modrzyk, Thibaut

AU - Levac, Brett

AU - Liaudat, Tobías I.

AU - Song, Maxime

AU - Hertrich, Johannes

AU - Neumayer, Sebastian

AU - Schramm, Georg

PY - 2025/11/19

Y1 - 2025/11/19

N2 - DeepInverse is an open-source PyTorch-based library for imaging inverse problems. DeepInverse implements all steps for image reconstruction, including efficient forward operators, defining and solving variational problems and designing and training advanced neural networks, for a wide set of domains (medical imaging, astronomical imaging, remote sensing, computational photography, compressed sensing and more).

AB - DeepInverse is an open-source PyTorch-based library for imaging inverse problems. DeepInverse implements all steps for image reconstruction, including efficient forward operators, defining and solving variational problems and designing and training advanced neural networks, for a wide set of domains (medical imaging, astronomical imaging, remote sensing, computational photography, compressed sensing and more).

U2 - 10.21105/joss.08923

DO - 10.21105/joss.08923

M3 - Article

SN - 2475-9066

VL - 10

JO - The Journal of Open Source Software

JF - The Journal of Open Source Software

IS - 115

M1 - 8923

ER -

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

Abstract

Access to Document

Fingerprint

Cite this