Monotonically Convergent Regularization by Denoising
- URL: http://arxiv.org/abs/2202.04961v1
- Date: Thu, 10 Feb 2022 11:32:41 GMT
- Title: Monotonically Convergent Regularization by Denoising
- Authors: Yuyang Hu, Jiaming Liu, Xiaojian Xu, and Ulugbek S. Kamilov
- Abstract summary: Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors.
Recent work has reported the state-of-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers.
This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior.
- Score: 19.631197002314305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Regularization by denoising (RED) is a widely-used framework for solving
inverse problems by leveraging image denoisers as image priors. Recent work has
reported the state-of-the-art performance of RED in a number of imaging
applications using pre-trained deep neural nets as denoisers. Despite the
recent progress, the stable convergence of RED algorithms remains an open
problem. The existing RED theory only guarantees stability for convex
data-fidelity terms and nonexpansive denoisers. This work addresses this issue
by developing a new monotone RED (MRED) algorithm, whose convergence does not
require nonexpansiveness of the deep denoising prior. Simulations on image
deblurring and compressive sensing recovery from random matrices show the
stability of MRED even when the traditional RED algorithm diverges.
Related papers
- Plug-and-Play image restoration with Stochastic deNOising REgularization [8.678250057211368]
We propose a new framework called deNOising REgularization (SNORE)
SNORE applies the denoiser only to images with noise of the adequate level.
It is based on an explicit regularization, which leads to a descent to solve inverse problems.
arXiv Detail & Related papers (2024-02-01T18:05:47Z) - Representing Noisy Image Without Denoising [91.73819173191076]
Fractional-order Moments in Radon space (FMR) is designed to derive robust representation directly from noisy images.
Unlike earlier integer-order methods, our work is a more generic design taking such classical methods as special cases.
arXiv Detail & Related papers (2023-01-18T10:13:29Z) - Zero-shot Blind Image Denoising via Implicit Neural Representations [77.79032012459243]
We propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs)
We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.
arXiv Detail & Related papers (2022-04-05T12:46:36Z) - Unsupervised PET Reconstruction from a Bayesian Perspective [12.512270202705404]
DeepRED is a typical representation that combines DIP and regularization by denoising (RED)
In this article, we leverage DeepRED from a Bayesian perspective to reconstruct PET images from a single corrupted sinogram without any supervised or auxiliary information.
arXiv Detail & Related papers (2021-10-29T06:32:21Z) - Unsupervised Single Image Super-resolution Under Complex Noise [60.566471567837574]
This paper proposes a model-based unsupervised SISR method to deal with the general SISR task with unknown degradations.
The proposed method can evidently surpass the current state of the art (SotA) method (about 1dB PSNR) not only with a slighter model (0.34M vs. 2.40M) but also faster speed.
arXiv Detail & Related papers (2021-07-02T11:55:40Z) - An Interpretation of Regularization by Denoising and its Application
with the Back-Projected Fidelity Term [55.34375605313277]
We show that the RED gradient can be seen as a (sub)gradient of a prior function--but taken at a denoised version of the point.
We propose to combine RED with the Back-Projection (BP) fidelity term rather than the common Least Squares (LS) term that is used in previous works.
arXiv Detail & Related papers (2021-01-27T18:45:35Z) - Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic
Method using Deep Denoising Priors [31.773305606551197]
Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors.
We propose a new asynchronous RED (ASYNC-RED) algorithm that enables asynchronous parallel processing of data, making it significantly faster than its serial counterparts for large-scale inverse problems.
arXiv Detail & Related papers (2020-10-03T23:55:36Z) - 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) - Regularization by Denoising via Fixed-Point Projection (RED-PRO) [34.89374374708481]
Regularization by Denoising (RED) and Plug-and-Play Prior (RED) are used in image processing.
While both have shown state-of-the-art results in various recovery tasks, their theoretical justification is incomplete.
arXiv Detail & Related papers (2020-08-01T09:35:22Z) - CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
We present a framework that models camera imaging pipeline in forward and reverse directions.
By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
arXiv Detail & Related papers (2020-03-17T15:20:25Z)
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.