Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser

by   Zahra Kadkhodaie, et al.

Prior probability models are a central component of many image processing problems, but density estimation is notoriously difficult for high-dimensional signals such as photographic images. Deep neural networks have provided state-of-the-art solutions for problems such as denoising, which implicitly rely on a prior probability model of natural images. Here, we develop a robust and general methodology for making use of this implicit prior. We rely on a little-known statistical result due to Miyasawa (1961), who showed that the least-squares solution for removing additive Gaussian noise can be written directly in terms of the gradient of the log of the noisy signal density. We use this fact to develop a stochastic coarse-to-fine gradient ascent procedure for drawing high-probability samples from the implicit prior embedded within a CNN trained to perform blind (i.e., unknown noise level) least-squares denoising. A generalization of this algorithm to constrained sampling provides a method for using the implicit prior to solve any linear inverse problem, with no additional training. We demonstrate this general form of transfer learning in multiple applications, using the same algorithm to produce high-quality solutions for deblurring, super-resolution, inpainting, and compressive sensing.


page 1

page 2

page 3

page 4

page 6

page 11

page 13

page 15


One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

While deep learning methods have achieved state-of-the-art performance i...

On Bayesian Estimation And Proximity Operators

There are two major routes to address the ubiquitous family of inverse p...

Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems

We consider the ubiquitous linear inverse problems with additive Gaussia...

Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting

We mainly analyze and solve the overfitting problem of deep image prior ...

Gradient Distribution Priors for Biomedical Image Processing

Ill-posed inverse problems are commonplace in biomedical image processin...

SNIPS: Solving Noisy Inverse Problems Stochastically

In this work we introduce a novel stochastic algorithm dubbed SNIPS, whi...

Robust Decoding from Binary Measurements with Cardinality Constraint Least Squares

The main goal of 1-bit compressive sampling is to decode n dimensional s...

Please sign up or login with your details

Forgot password? Click here to reset