Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images

被引:14
作者
Dutta, Sayantan [1 ,2 ]
Basarab, Adrian [1 ]
Georgeot, Bertrand [2 ]
Kouame, Denis [1 ]
机构
[1] Univ Toulouse, UMR CNRS 5505, Inst Rech Informat Toulouse, F-31062 Toulouse, France
[2] Univ Toulouse, CNRS, Lab Phys Theor, UPS, F-31062 Toulouse, France
关键词
Adaptation models; Optimization; Noise reduction; Image restoration; Deconvolution; Noise measurement; Convex functions; Poisson deconvolution; plug-and-play; ADMM; quantum denoiser; adaptive denoiser; quantum image processing; ALTERNATING DIRECTION METHOD; INVERSE PROBLEMS; SIGNAL RECOVERY; ALGORITHM; SPARSE; DECONVOLUTION; CONVERGENCE; FRAMEWORK; REGULARIZATION; REPRESENTATION;
D O I
10.1109/ACCESS.2021.3118608
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:139771 / 139791
页数:21
相关论文
共 111 条
[61]   Implementation of high-order variational models made easy for image processing [J].
Lu, Wenqi ;
Duan, Jinming ;
Qiu, Zhaowen ;
Pan, Zhenkuan ;
Liu, Ryan Wen ;
Bai, Li .
MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2016, 39 (14) :4208-4233
[62]   Using Deep Neural Networks for Inverse Problems in Imaging Beyond analytical methods [J].
Lucas, Alice ;
Iliadis, Michael ;
Molina, Rafael ;
Katsaggelos, Aggelos K. .
IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (01) :20-36
[63]   A Closed-Form Approximation of the Exact Unbiased Inverse of the Anscombe Variance-Stabilizing Transformation [J].
Makitalo, Markku ;
Foi, Alessandro .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (09) :2697-2698
[64]   Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising [J].
Makitalo, Markku ;
Foi, Alessandro .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (01) :99-109
[65]   Symmetrizing Smoothing Filters [J].
Milanfar, Peyman .
SIAM JOURNAL ON IMAGING SCIENCES, 2013, 6 (01) :263-284
[66]  
Moreau JJ., 1965, Bull Soc Math Fr, V93, P273, DOI [10.24033/bsmf.1625, DOI 10.24033/BSMF.1625]
[67]  
Morin R, 2012, 2012 9TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), P1595, DOI 10.1109/ISBI.2012.6235880
[68]   A Holistic Approach to Cross-Channel Image Noise Modeling and its Application to Image Denoising [J].
Nam, Seonghyeon ;
Hwang, Youngbae ;
Matsushita, Yasuyuki ;
Kim, Seon Joo .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :1683-1691
[69]   CoSaMP: Iterative signal recovery from incomplete and inaccurate samples [J].
Needell, D. ;
Tropp, J. A. .
APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2009, 26 (03) :301-321
[70]   A statistical multiscale framework for Poisson inverse problems [J].
Nowak, RD ;
Kolaczyk, ED .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2000, 46 (05) :1811-1825