Ground Truth Free Denoising by Optimal Transport
From MaRDI portal
Publication:6344348
arXiv2007.01575MaRDI QIDQ6344348FDOQ6344348
Authors: Sören Dittmer, Carola-Bibiane Schönlieb, Peter Maass 
Publication date: 3 July 2020
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.
Has companion code repository: https://github.com/sdittmer/gtfd
This page was built for publication: Ground Truth Free Denoising by Optimal Transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6344348)
