Log In Sign Up

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors

by   Gauri Jagatap, et al.

Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned generative priors they do not require any training over large datasets. However, few theoretical guarantees exist in the scope of using untrained network priors for inverse imaging problems. We explore new applications and theory for untrained network priors. Specifically, we consider the problem of solving linear inverse problems, such as compressive sensing, as well as non-linear problems, such as compressive phase retrieval. We model images to lie in the range of an untrained deep generative network with a fixed seed. We further present a projected gradient descent scheme that can be used for both compressive sensing and phase retrieval and provide rigorous theoretical guarantees for its convergence. We also show both theoretically as well as empirically that with deep network priors, one can achieve better compression rates for the same image quality compared to hand crafted priors.


page 9

page 10


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...

Theoretical Perspectives on Deep Learning Methods in Inverse Problems

In recent years, there have been significant advances in the use of deep...

DAEs for Linear Inverse Problems: Improved Recovery with Provable Guarantees

Generative priors have been shown to provide improved results over spars...

Signal Recovery with Non-Expansive Generative Network Priors

We study compressive sensing with a deep generative network prior. Initi...

Exact asymptotics for phase retrieval and compressed sensing with random generative priors

We consider the problem of compressed sensing and of (real-valued) phase...

Unrolled Optimization with Deep Priors

A broad class of problems at the core of computational imaging, sensing,...

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

The plug-and-play priors (PnP) and regularization by denoising (RED) met...