DAEs for Linear Inverse Problems: Improved Recovery with Provable Guarantees

01/13/2021
by   Jasjeet Dhaliwal, et al.
7

Generative priors have been shown to provide improved results over sparsity priors in linear inverse problems. However, current state of the art methods suffer from one or more of the following drawbacks: (a) speed of recovery is slow; (b) reconstruction quality is deficient; (c) reconstruction quality is contingent on a computationally expensive process of tuning hyperparameters. In this work, we address these issues by utilizing Denoising Auto Encoders (DAEs) as priors and a projected gradient descent algorithm for recovering the original signal. We provide rigorous theoretical guarantees for our method and experimentally demonstrate its superiority over existing state of the art methods in compressive sensing, inpainting, and super-resolution. We find that our algorithm speeds up recovery by two orders of magnitude (over 100x), improves quality of reconstruction by an order of magnitude (over 10x), and does not require tuning hyperparameters.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

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
06/20/2019

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors

Deep neural networks as image priors have been recently introduced for p...
research
06/29/2022

Theoretical Perspectives on Deep Learning Methods in Inverse Problems

In recent years, there have been significant advances in the use of deep...
research
05/28/2019

Invertible generative models for inverse problems: mitigating representation error and dataset bias

Trained generative models have shown remarkable performance as priors fo...
research
06/07/2021

Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition

The plug-and-play priors (PnP) and regularization by denoising (RED) met...
research
04/20/2023

Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization

We introduce a novel optimization algorithm for image recovery under lea...
research
08/07/2016

ShapeFit and ShapeKick for Robust, Scalable Structure from Motion

We introduce a new method for location recovery from pair-wise direction...

Please sign up or login with your details

Forgot password? Click here to reset