We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals. The training is solely based on samples of noisy data and examples of noise, which -- critically -- do not need to come in pairs. We only need the assumption that the noise is independent and additive (although we describe how this can be extended). The method rests on a Wasserstein Generative Adversarial Network setting, which utilizes two critics and one generator.
@article{arxiv.2007.01575,
title = {Ground Truth Free Denoising by Optimal Transport},
author = {Sören Dittmer and Carola-Bibiane Schönlieb and Peter Maass},
journal= {arXiv preprint arXiv:2007.01575},
year = {2020}
}