Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing

by   Mohammadreza Soltani, et al.

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are easily available. However, in many applications, this assumption is violated. In this paper, we consider the observation setting when the samples from target distribution are given by the superposition of two structured components and leverage GANs for learning the structure of the components. We propose two novel frameworks: denoising-GAN and demixing-GAN. The denoising-GAN assumes access to clean samples from the second component and try to learn the other distribution, whereas demixing-GAN learns the distribution of the components at the same time. Through extensive numerical experiments, we demonstrate that proposed frameworks can generate clean samples from unknown distributions, and provide competitive performance in tasks such as denoising, demixing, and compressive sensing.


page 9

page 10

page 13

page 16

page 17

page 18

page 20

page 22


Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...

Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks

Generative adversarial networks (GANs) are known for their strong abilit...

City-GAN: Learning architectural styles using a custom Conditional GAN architecture

Generative Adversarial Networks (GANs) are a well-known technique that i...

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

A wide variety of deep generative models has been developed in the past ...

Correction by Projection: Denoising Images with Generative Adversarial Networks

Generative adversarial networks (GANs) transform low-dimensional latent ...

Towards Adversarial Denoising of Radar Micro-Doppler Signatures

Generative Adversarial Networks (GANs) are considered the state-of-the-a...

Evaluating Generative Adversarial Networks on Explicitly Parameterized Distributions

The true distribution parameterizations of commonly used image datasets ...

Please sign up or login with your details

Forgot password? Click here to reset