Published on Fri Jul 03 2020

Ground Truth Free Denoising by Optimal Transport

Sören Dittmer, Carola-Bibiane Schönlieb, Peter Maass

We present a learned unsupervised denoising method for arbitrary types of data. The training is solely based on samples of noisy data and examples of noise. The method rests on a Wasserstein Generative Adversarial Network.

0
0
0
Abstract

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.