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

被引:10
|
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 50 条
  • [1] PLUG-AND-PLAY AUDIO RESTORATION WITH DIFFUSION DENOISER
    Svento, Michal
    Rajmic, Pavel
    Mokry, Ondrej
    2024 18TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT, IWAENC 2024, 2024, : 115 - 119
  • [2] Plug-and-Play Image Restoration With Deep Denoiser Prior
    Zhang, Kai
    Li, Yawei
    Zuo, Wangmeng
    Zhang, Lei
    Van Gool, Luc
    Timofte, Radu
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (10) : 6360 - 6376
  • [3] Poisson Image Deconvolution by a Plug-and-Play Quantum Denoising Scheme
    Dutta, Sayantan
    Basarab, Adrian
    Georgeot, Bertrand
    Kouame, Denis
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 646 - 650
  • [4] Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization
    Hurault, Samuel
    Leclaire, Arthur
    Papadakis, Nicolas
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [5] Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling
    Xu, Xiaojian
    Liu, Jiaming
    Sun, Yu
    Wohlberg, Brendt
    Kamilov, Ulugbek S.
    2020 54TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2020, : 1305 - 1312
  • [6] Convergent Plug-and-Play with Proximal Denoiser and Unconstrained Regularization Parameter
    Hurault, Samuel
    Chambolle, Antonin
    Leclaire, Arthur
    Papadakis, Nicolas
    JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2024, 66 (04) : 616 - 638
  • [7] A Plug-and-Play Deep Denoiser Prior Model for Accelerated MRI Reconstruction
    Karaoglu, Hasan H.
    Eksioglu, Ender M.
    2022 45TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING, TSP, 2022, : 260 - 263
  • [8] Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration
    Le Pendu, Mikael
    Guillemot, Christine
    SIAM JOURNAL ON IMAGING SCIENCES, 2023, 16 (01): : 393 - 422
  • [9] CurvPnP: Plug-and-play blind image restoration with deep curvature denoiser
    Li, Yutong
    Chang, Huibin
    Duan, Yuping
    SIGNAL PROCESSING, 2025, 233
  • [10] Poisson inverse problems by the Plug-and-Play scheme
    Rond, Arie
    Giryes, Raja
    Elad, Michael
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 41 : 96 - 108