Learning pseudo-contractive denoisers for inverse problems
Preprint
Abstract
Deep denoisers have shown excellent performance in solving inverse problems in signal and image processing. In order to guarantee the convergence, the denoiser needs to satisfy some Lipschitz conditions like non-expansiveness. However, enforcing such constraints inevitably compromises recovery performance. This paper introduces a novel training strategy that enforces a weaker constraint on the deep denoiser called pseudo-contractiveness. By studying the spectrum of the Jacobian matrix, relationships between different denoiser assumptions are revealed. Effective algorithms based on gradient descent and Ishikawa process are derived, and further assumptions of strict pseudo-contractiveness yield efficient algorithms using half-quadratic splitting and forward-backward splitting. The proposed algorithms theoretically converge strongly to a fixed point. A training strategy based on holomorphic transformation and functional calculi is proposed to enforce the pseudo-contractive denoiser assumption. Extensive experiments demonstrate superior performance of the pseudo-contractive denoiser compared to related denoisers. The proposed methods are competitive in terms of visual effects and quantitative values.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- On Maximum a Posteriori Estimation with Plug & Play Priors and Stochastic Gradient DescentJournal of Mathematical Imaging and Vision, 2023
- Regularization by Denoising: Clarifications and New InterpretationsIEEE Transactions on Computational Imaging, 2018
- Tight global linear convergence rate bounds for Douglas–Rachford splittingJournal of Fixed Point Theory and Applications, 2017
- Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and ApplicationsIEEE Transactions on Computational Imaging, 2016
- Plug-and-Play Priors for Bright Field Electron Tomography and Sparse InterpolationIEEE Transactions on Computational Imaging, 2016
- Splitting Methods with Variable Metric for Kurdyka–Łojasiewicz Functions and General Convergence RatesJournal of Optimization Theory and Applications, 2014
- On Mann iteration in Hilbert spacesNonlinear Analysis, 2007
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992
- Bayesian estimation of transmission tomograms using segmentation based optimizationIEEE Transactions on Nuclear Science, 1992
- On the Mann iteration process in a Hilbert spaceJournal of Mathematical Analysis and Applications, 1977