Noise2Noise is an AI denoiser trained with noisy images only. We implemented a ligther version which trains faster on smaller pictures without losing performance and an even simpler one where every low-level component was implemented from scratch, including a reimplementation of autograd.
python pytorch autograd unet noise-reduction 2d-convolution adam-optimizer sigmoid-function mean-square-error noise2noise pytorch-framework pytorch-implementation denoiser denoiser-network relu-activation autograd-engine sequential-pytorch
-
Updated
Sep 25, 2022 - Jupyter Notebook