DeepInverse: a Pytorch library for imaging with deep learning

Test Status Docs Status Python 3.6+ codecov Black

Deep Inverse is a Pytorch based library for solving imaging inverse problems with deep learning.

Github repository: https://github.com/deepinv/deepinv.

Featuring

_images/deepinv_schematic.png

Installation

Install the latest version of deepinv via pip:

pip install deepinv

You can also install the latest version of deepinv directly from github:

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

Getting Started

Try out one of the following deblurring examples (or pick from full list of examples):

Image deblurring with custom deep explicit prior.

Image deblurring with custom deep explicit prior.

A tour of blur operators

A tour of blur operators

Image deblurring with Total-Variation (TV) prior

Image deblurring with Total-Variation (TV) prior

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

Building your custom sampling algorithm.

Building your custom sampling algorithm.

Implementing DiffPIR

Implementing DiffPIR

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring

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 is to open an issue on the issue tracker.

Lead Developers

Julian Tachella, Dongdong Chen, Samuel Hurault, Matthieu Terris and Andrew Wang.