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.

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 the latest stable release of deepinv:

pip install deepinv

For more information, check out the DeepInverse GitHub repo and our documentation.