Ground Truth Free Denoising by Optimal Transport

07/03/2020

∙

by   Sören Dittmer, et al.

∙

0

∙

share

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.