deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
This project helps researchers and practitioners in imaging science restore degraded images using deep learning techniques. You input a blurry, noisy, or otherwise corrupted image and receive a clearer, reconstructed version. It's designed for imaging scientists, machine learning engineers, and signal processing researchers working on image restoration, medical imaging, or computational photography.
674 stars. Actively maintained with 15 commits in the last 30 days. Available on PyPI.
Use this if you need to restore or enhance degraded images and want to leverage state-of-the-art deep learning methods for tasks like denoising, deblurring, or compressed sensing.
Not ideal if you are looking for a simple, off-the-shelf image editor for general consumer use or if you are not comfortable with deep learning concepts.
Stars
674
Forks
151
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 11, 2026
Commits (30d)
15
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/deepinv/deepinv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.
oeway/pytorch-deform-conv
PyTorch implementation of Deformable Convolution