Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images
arXiv:2107.00407 · doi:10.1109/ACCESS.2021.3118608
Abstract
A new Plug-and-Play (PnP) alternating direction of multipliers (ADMM) scheme is proposed in this paper, by embedding a recently introduced adaptive denoiser using the Schroedinger equation's solutions of quantum physics. The potential of the proposed model is studied for Poisson image deconvolution, which is a common problem occurring in number of imaging applications, such as limited photon acquisition or X-ray computed tomography. Numerical results show the efficiency and good adaptability of the proposed scheme compared to recent state-of-the-art techniques, for both high and low signal-to-noise ratio scenarios. This performance gain regardless of the amount of noise affecting the observations is explained by the flexibility of the embedded quantum denoiser constructed without anticipating any prior statistics about the noise, which is one of the main advantages of this method. The main novelty of this work resided in the integration of a modified quantum denoiser into the PnP-ADMM framework and the numerical proof of convergence of the resulting algorithm.
arXiv comment22 pages, 13 figures; complements and expands arXiv:2010.09321
References in corpus (15)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- An overview of gradient descent optimization algorithms
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
- Restoration of Poissonian Images Using Alternating Direction Optimization
- Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation
- This is SPIRAL-TAP: Sparse Poisson Intensity Reconstruction ALgorithms - Theory and Practice
- A proximal iteration for deconvolving Poisson noisy images using sparse representations
- Deconvolving Images with Unknown Boundaries Using the Alternating Direction Method of Multipliers
- Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
- Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
- Provable Convergence of Plug-and-Play Priors with MMSE denoisers
- Quantum mechanics-based signal and image representation: application to denoising
- Adaptive transform via quantum signal processing: application to signal and image denoising