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

02/26/2019
by   Ankit Raj, et al.
0

A Generative Adversarial Network (GAN) with generator G trained to model the prior of images has been shown to perform better than sparsity-based regularizers in ill-posed inverse problems. In this work, we propose a new method of deploying a GAN-based prior to solve linear inverse problems using projected gradient descent (PGD). Our method learns a network-based projector for use in the PGD algorithm, eliminating the need for expensive computation of the Jacobian of G. Experiments show that our approach provides a speed-up of 30-40× over earlier GAN-based recovery methods for similar accuracy in compressed sensing. Our main theoretical result is that if the measurement matrix is moderately conditioned for range(G) and the projector is δ-approximate, then the algorithm is guaranteed to reach O(δ) reconstruction error in O(log(1/δ)) steps in the low noise regime. Additionally, we propose a fast method to design such measurement matrices for a given G. Extensive experiments demonstrate the efficacy of this method by requiring 5-10× fewer measurements than random Gaussian measurement matrices for comparable recovery performance.

READ FULL TEXT

page 5

page 6

research
09/02/2021

Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent

The projected gradient descent (PGD) method has shown to be effective in...
research
01/15/2019

Using auto-encoders for solving ill-posed linear inverse problems

Compressed sensing algorithms recover a signal from its under-determined...
research
02/23/2018

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

In recent works, both sparsity-based methods as well as learning-based m...
research
10/23/2018

Reproducing AmbientGAN: Generative models from lossy measurements

In recent years, Generative Adversarial Networks (GANs) have shown subst...
research
05/12/2019

Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems

Extracting information from nonlinear measurements is a fundamental chal...
research
10/24/2021

WARPd: A linearly convergent first-order method for inverse problems with approximate sharpness conditions

Reconstruction of signals from undersampled and noisy measurements is a ...
research
03/02/2021

Structural Sparsity in Multiple Measurements

We propose a novel sparsity model for distributed compressed sensing in ...

Please sign up or login with your details

Forgot password? Click here to reset