tachella/unsure
code related to "UNSURE: Unknown Noise level Stein's Unbiased Risk Estimator" by Tachella, Davies and Jacques
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.
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.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!