English

Ground Truth Free Denoising by Optimal Transport

Computer Vision and Pattern Recognition 2020-07-06 v1 Neural and Evolutionary Computing Functional Analysis Optimization and Control

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T16:49:29.408Z