Block Coordinate Plug-and-Play Methods for Blind Inverse Problems
- URL: http://arxiv.org/abs/2305.12672v2
- Date: Thu, 26 Oct 2023 23:37:38 GMT
- Title: Block Coordinate Plug-and-Play Methods for Blind Inverse Problems
- Authors: Weijie Gan, Shirin Shoushtari, Yuyang Hu, Jiaming Liu, Hongyu An,
Ulugbek S. Kamilov
- Abstract summary: Plug-and-play prior is a well-known method for solving inverse problems by operators combining physical measurement models and learned image denoisers.
While.
methods have been extensively used for image recovery with known measurement operators, there is little work on.
solving blind inverse problems.
We address this gap by presenting learned denoisers as priors on both unknown operators.
- Score: 13.543612162739773
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Plug-and-play (PnP) prior is a well-known class of methods for solving
imaging inverse problems by computing fixed-points of operators combining
physical measurement models and learned image denoisers. While PnP methods have
been extensively used for image recovery with known measurement operators,
there is little work on PnP for solving blind inverse problems. We address this
gap by presenting a new block-coordinate PnP (BC-PnP) method that efficiently
solves this joint estimation problem by introducing learned denoisers as priors
on both the unknown image and the unknown measurement operator. We present a
new convergence theory for BC-PnP compatible with blind inverse problems by
considering nonconvex data-fidelity terms and expansive denoisers. Our theory
analyzes the convergence of BC-PnP to a stationary point of an implicit
function associated with an approximate minimum mean-squared error (MMSE)
denoiser. We numerically validate our method on two blind inverse problems:
automatic coil sensitivity estimation in magnetic resonance imaging (MRI) and
blind image deblurring. Our results show that BC-PnP provides an efficient and
principled framework for using denoisers as PnP priors for jointly estimating
measurement operators and images.
Related papers
- PnP-Flow: Plug-and-Play Image Restoration with Flow Matching [2.749898166276854]
We introduce Plug-and-Play Flow Matching, an algorithm for solving inverse imaging problems.
We evaluate its performance on denoising, superresolution, and inpainting tasks.
arXiv Detail & Related papers (2024-10-03T12:13:56Z) - Single-Shot Plug-and-Play Methods for Inverse Problems [18.260678080538888]
Plug-and-Play priors in inverse problems have become increasingly prominent in recent years.
Existing models predominantly rely on pre-trained denoisers using large datasets.
In this work, we introduce Single-Shot perturbative methods, shifting the focus to solving inverse problems with minimal data.
arXiv Detail & Related papers (2023-11-22T20:31:33Z) - Convergent regularization in inverse problems and linear plug-and-play
denoisers [3.759634359597638]
Plug-and-play () denoising is a popular framework for solving imaging problems using inverse image denoisers.
Not much is known about the properties of the converged solution as the noise level in the measurement vanishes to zero, i.e. whether provably convergent regularization schemes are provably convergent regularization schemes.
We show that with linear denoisers, the implicit regularization of the denoiser to an explicit regularization functional leads to a convergent regularization scheme.
arXiv Detail & Related papers (2023-07-18T17:16:08Z) - Provably Convergent Plug-and-Play Quasi-Newton Methods [5.9974035827998655]
We propose an efficient method to combine fidelity terms and deep denoisers.
We show that the proposed quasi-Newton algorithm is critical points of a weakly convex function.
Experiments on imageblurring and super-resolution demonstrate faster convergence as compared to other provable deM methods.
arXiv Detail & Related papers (2023-03-09T20:09:15Z) - GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse
Problems with Denoising Diffusion Restoration [64.8770356696056]
We propose GibbsDDRM, an extension of Denoising Diffusion Restoration Models (DDRM) to a blind setting in which the linear measurement operator is unknown.
The proposed method is problem-agnostic, meaning that a pre-trained diffusion model can be applied to various inverse problems without fine-tuning.
arXiv Detail & Related papers (2023-01-30T06:27:48Z) - JPEG Artifact Correction using Denoising Diffusion Restoration Models [110.1244240726802]
We build upon Denoising Diffusion Restoration Models (DDRM) and propose a method for solving some non-linear inverse problems.
We leverage the pseudo-inverse operator used in DDRM and generalize this concept for other measurement operators.
arXiv Detail & Related papers (2022-09-23T23:47:00Z) - Regularization by Denoising Sub-sampled Newton Method for Spectral CT
Multi-Material Decomposition [78.37855832568569]
We propose to solve a model-based maximum-a-posterior problem to reconstruct multi-materials images with application to spectral CT.
In particular, we propose to solve a regularized optimization problem based on a plug-in image-denoising function.
We show numerical and experimental results for spectral CT materials decomposition.
arXiv Detail & Related papers (2021-03-25T15:20:10Z) - Learned Block Iterative Shrinkage Thresholding Algorithm for
Photothermal Super Resolution Imaging [52.42007686600479]
We propose a learned block-sparse optimization approach using an iterative algorithm unfolded into a deep neural network.
We show the benefits of using a learned block iterative shrinkage thresholding algorithm that is able to learn the choice of regularization parameters.
arXiv Detail & Related papers (2020-12-07T09:27:16Z) - Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
Blind image restoration is a common yet challenging problem in computer vision.
We propose a novel blind image restoration method, aiming to integrate both the advantages of them.
Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
arXiv Detail & Related papers (2020-08-25T03:30:53Z) - A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems [5.025654873456756]
We propose an efficient plug-and-play ( inverse problems) algorithm for imaging applications.
Our results demonstrate effectiveness of our approach compared with state-of-the-art methods.
arXiv Detail & Related papers (2020-06-20T18:03:52Z) - Solving Inverse Problems with a Flow-based Noise Model [100.18560761392692]
We study image inverse problems with a normalizing flow prior.
Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements.
We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns.
arXiv Detail & Related papers (2020-03-18T08:33:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.