Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees

Abstract

In recent works, both sparsity-based methods as well as learning-based methods have proven to be successful in solving several challenging linear inverse problems. However, sparsity priors for natural signals and images suffer from poor discriminative capability, while learning-based methods seldom provide concrete theoretical guarantees. In this work, we advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing. In particular, we propose a projected gradient descent (PGD) algorithm for effective use of GAN priors for linear inverse problems, and also provide theoretical guarantees on the rate of convergence of this algorithm. Moreover, we show empirically that our algorithm demonstrates superior performance over an existing method of leveraging GANs for compressive sensing.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Neural Photo Editing with Introspective Adversarial Networks
• Generative Visual Manipulation on the Natural Image Manifold
• One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
• Deep Learning-Guided Image Reconstruction from Incomplete Data
• Learning to Invert: Signal Recovery via Deep Convolutional Networks

Cited by in corpus (7)

• MR image reconstruction using deep density priors
• Compressed Sensing with Deep Image Prior and Learned Regularization
• An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
• Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
• Deep Learning Techniques for Inverse Problems in Imaging
• Blind Image Deconvolution using Pretrained Generative Priors
• Inverting Deep Generative models, One layer at a time