Reproducing AmbientGAN: Generative models from lossy measurements

by   Mehdi Ahmadi, et al.
Université INRS
Corporation de l'ecole Polytechnique de Montreal
Université de Montréal
McGill University

In recent years, Generative Adversarial Networks (GANs) have shown substantial progress in modeling complex distributions of data. These networks have received tremendous attention since they can generate implicit probabilistic models that produce realistic data using a stochastic procedure. While such models have proven highly effective in diverse scenarios, they require a large set of fully-observed training samples. In many applications access to such samples are difficult or even impractical and only noisy or partial observations of the desired distribution is available. Recent research has tried to address the problem of incompletely observed samples to recover the distribution of the data. zhu2017unpaired and yeh2016semantic proposed methods to solve ill-posed inverse problem using cycle-consistency and latent-space mappings in adversarial networks, respectively. bora2017compressed and kabkab2018task have applied similar adversarial approaches to the problem of compressed sensing. In this work, we focus on a new variant of GAN models called AmbientGAN, which incorporates a measurement process (e.g. adding noise, data removal and projection) into the GAN training. While in the standard GAN, the discriminator distinguishes a generated image from a real image, in AmbientGAN model the discriminator has to separate a real measurement from a simulated measurement of a generated image. The results shown by bora2018ambientgan are quite promising for the problem of incomplete data, and have potentially important implications for generative approaches to compressed sensing and ill-posed problems.


page 4

page 6


Task-Aware Compressed Sensing with Generative Adversarial Networks

In recent years, neural network approaches have been widely adopted for ...

Bidirectional Conditional Generative Adversarial Networks

Conditional variants of Generative Adversarial Networks (GANs), known as...

GAN-based Projector for Faster Recovery in Compressed Sensing with Convergence Guarantees

A Generative Adversarial Network (GAN) with generator G trained to model...

Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery

Image restoration is a typical ill-posed problem, and it contains variou...

Regression with Conditional GAN

In recent years, impressive progress has been made in the design of impl...

Mining GOLD Samples for Conditional GANs

Conditional generative adversarial networks (cGANs) have gained a consid...

Please sign up or login with your details

Forgot password? Click here to reset