tachella/unsure

code related to "UNSURE: Unknown Noise level Stein's Unbiased Risk Estimator" by Tachella, Davies and Jacques

33
/ 100
Emerging

This project helps machine learning researchers and practitioners train image reconstruction neural networks, even when the exact level or type of noise corrupting the input data is unknown. It takes noisy measurements, typically images, and outputs a trained network capable of generating cleaner, reconstructed images. This is particularly useful for those working with real-world sensor data or medical imaging where noise characteristics can be unpredictable.

Use this if you need to train a neural network to reconstruct clean images from noisy observations but lack precise information about the noise properties (like its variance or distribution).

Not ideal if you already have a well-defined noise model and can accurately estimate its parameters, as simpler methods might suffice.

image-reconstruction self-supervised-learning denoising computational-imaging medical-imaging
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

BSD-3-Clause

Last pushed

Nov 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tachella/unsure"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.