An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks

TL;DR

This paper introduces an unsupervised method using pre-trained GANs to solve various inverse problems without needing explicit measurement models or large paired datasets, demonstrating promising results in multiple applications.

Contribution

It presents a novel unsupervised approach leveraging GANs for inverse problems, eliminating the need for explicit measurement models and large training datasets.

Findings

Outperforms several baseline methods in experiments

Effective in blind source separation, deblurring, and edge map recovery

Works without knowledge of measurement processes

Abstract

Solving inverse problems continues to be a challenge in a wide array of applications ranging from deblurring, image inpainting, source separation etc. Most existing techniques solve such inverse problems by either explicitly or implicitly finding the inverse of the model. The former class of techniques require explicit knowledge of the measurement process which can be unrealistic, and rely on strong analytical regularizers to constrain the solution space, which often do not generalize well. The latter approaches have had remarkable success in part due to deep learning, but require a large collection of source-observation pairs, which can be prohibitively expensive. In this paper, we propose an unsupervised technique to solve inverse problems with generative adversarial networks (GANs). Using a pre-trained GAN in the space of source signals, we show that one can reliably recover solutions to under determined problems in a `blind' fashion, i.e., without knowledge of the measurement process. We solve this by making successive estimates on the model and the solution in an iterative fashion. We show promising results in three challenging applications -- blind source separation, image deblurring, and recovering an image from its edge map, and perform better than several baselines.