The standard approach to image reconstruction using deep learning is to use clean image priors for training purposes. In this project, we attempt to achieve denoising without using a clean image prior and yet, achieving a performance comparable to, or sometimes, even better than that obtained using the conventional approach.
tensorflow
image-processing
dataset
autoencoder
unet
denoising-autoencoders
image-restoration
denoising
rednet
noise2noise
gaussian-noise
image-data-generator
bsd500
-
Updated
Dec 10, 2022 - Jupyter Notebook