• Paper
This is a simple implementation of the Noise2Noise paper (Lehtinen et al., 2018).
It requires torch, torchvision, numpy, matlplotlib and tqdm. It can be installed this way:
pip install -r requirements.txt
I used 32x32 images from ImageNet with random gaussian noise. The images are available in the form of pickle files for PyTorch. Pretrained weights are also available on this Drive.
A demo Jupyter Notebook is available here: .
A full report on this implementation can be found here.