2020/07/03 by Dittmer, Sören, Schönlieb, Carola-Bibiane, Maass, Peter
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Mathematics #Functional Analysis (math.FA) #Neural and Evolutionary Computing (cs.NE) #Optimization and Control (math.OC)
paper · doi:10.48550/arxiv.2007.01575
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.