nhauber99/degradr
Python library for realistically degrading images.
This helps researchers and machine learning engineers create more realistic training data for computer vision models. It takes a pristine, high-quality image as input and applies a series of real-world degradations like blur, noise, and compression. The output is a synthetic, degraded version of the original image, useful for training models to be robust in real-world conditions.
No commits in the last 6 months.
Use this if you need to simulate realistic image imperfections for tasks like training computer vision models or testing image processing algorithms.
Not ideal if you are a casual user looking for a simple, plug-and-play image degradation tool without any setup.
Stars
22
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nhauber99/degradr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
CAREamics/careamics
A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN...
yu4u/noise2noise
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration...
rgeirhos/texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased...
NICALab/SUPPORT
Accurate denoising of voltage imaging data through statistically unbiased prediction, Nature Methods.
jaewon-lee-b/lte
Local Texture Estimator for Implicit Representation Function, in CVPR 2022