DeepInverse: A Python package for solving imaging inverse problems with deep learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915348095172608 |
|---|---|
| author | Tachella, Julián Terris, Matthieu Hurault, Samuel Wang, Andrew Chen, Dongdong Nguyen, Minh-Hai Song, Maxime Davies, Thomas Davy, Leo Dong, Jonathan Escande, Paul Hertrich, Johannes Hu, Zhiyuan Liaudat, Tobías I. Laurent, Nils Levac, Brett Massias, Mathurin Moreau, Thomas Modrzyk, Thibaut Monroy, Brayan Neumayer, Sebastian Scanvic, Jérémy Sarron, Florian Sechaud, Victor Schramm, Georg Vo, Romain Weiss, Pierre |
| author_facet | Tachella, Julián Terris, Matthieu Hurault, Samuel Wang, Andrew Chen, Dongdong Nguyen, Minh-Hai Song, Maxime Davies, Thomas Davy, Leo Dong, Jonathan Escande, Paul Hertrich, Johannes Hu, Zhiyuan Liaudat, Tobías I. Laurent, Nils Levac, Brett Massias, Mathurin Moreau, Thomas Modrzyk, Thibaut Monroy, Brayan Neumayer, Sebastian Scanvic, Jérémy Sarron, Florian Sechaud, Victor Schramm, Georg Vo, Romain Weiss, Pierre |
| contents | DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementation of forward operators (e.g., optics, MRI, tomography), to the definition and resolution of variational problems and the design and training of advanced neural network architectures. In this paper, we describe the main functionality of the library and discuss the main design choices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20160 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeepInverse: A Python package for solving imaging inverse problems with deep learning Tachella, Julián Terris, Matthieu Hurault, Samuel Wang, Andrew Chen, Dongdong Nguyen, Minh-Hai Song, Maxime Davies, Thomas Davy, Leo Dong, Jonathan Escande, Paul Hertrich, Johannes Hu, Zhiyuan Liaudat, Tobías I. Laurent, Nils Levac, Brett Massias, Mathurin Moreau, Thomas Modrzyk, Thibaut Monroy, Brayan Neumayer, Sebastian Scanvic, Jérémy Sarron, Florian Sechaud, Victor Schramm, Georg Vo, Romain Weiss, Pierre Image and Video Processing 65F22, 68T07 I.4.4; I.4.5; I.2.6 DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementation of forward operators (e.g., optics, MRI, tomography), to the definition and resolution of variational problems and the design and training of advanced neural network architectures. In this paper, we describe the main functionality of the library and discuss the main design choices. |
| title | DeepInverse: A Python package for solving imaging inverse problems with deep learning |
| topic | Image and Video Processing 65F22, 68T07 I.4.4; I.4.5; I.2.6 |
| url | https://arxiv.org/abs/2505.20160 |