Plug-and-Play priors for model based reconstruction
The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Model-based reconstruction is a powerful framework for solving a variety of inverse problems in imaging. In recent years, enormous progress has been made in the problem of denoising, a special case of an inverse problem where the forward model is an identity operator. Similarly, great progress has been made in improving model-based inversion when the forward model corresponds to complex physical measurements in applications such as X-ray CT, electron-microscopy, MRI, and ultrasound, to name just a few. However, combining state-of-the-art denoising algorithms (i.e., prior models) with state-of-the-art inversion methods (i.e., forward models) has been a challenge for many reasons. In this paper, we propose a flexible framework that allows state-of-the-art forward models of imaging systems to be matched with state-of-the-art priors or denoising models. This framework, which we term as Plug-and-Play priors, has the advantage that it dramatically simplifies software integration, and moreover, it allows state-of-the-art denoising methods that have no known formulation as an optimization problem to be used. We demonstrate with some simple examples how Plug-and-Play priors can be used to mix and match a wide variety of existing denoising models with a tomographic forward model, thus greatly expanding the range of possible problem solutions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A Threshold Selection Method from Gray-Level Histograms
Otsu, N. (1979) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1979.4310076 · Cited by 43,398 · cited 1×
“In order to initialize the class labels b we use Otsu’s method [30] on a low pass filtered version of the noisy input y.”
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
Nonlinear total variation based noise removal algorithms
Rudin, L. I., Osher, S., & Fatemi, E. (1992) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(92)90242-f · Cited by 15,704 · cited 1×
“We compare reconstructions using the Plug-andPlay priors framework by experimenting with six different denoising techniques/priors - K-SVD [4], BM3D [5], PLOW [7], Total Variation (TV) [21], q-GGMRF [22] and discrete reconstruction (DR) [23].”
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
Image denoising by sparse 3-D transform-domain collaborative filtering
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.901238 · Cited by 9,283 · cited 3×
“We compare reconstructions using the Plug-andPlay priors framework by experimenting with six different denoising techniques/priors - K-SVD [4], BM3D [5], PLOW [7], Total Variation (TV) [21], q-GGMRF [22] and discrete reconstruction (DR) [23].”
A Non-Local Algorithm for Image Denoising
Buades, A., Coll, B., & Morel, J.-M. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.38 · Cited by 7,616 · cited 1×
“Examples of new methods include a wide variety of patch based non-local means approaches [3], generalizations of bi-lateral filtering approaches [1], patch-based dictionary learning methods such as K-SVD [4], block-matching with transform-based denoising such as BM3D [5], and a variety of total-variation [2], and Mark…”
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321 · cited 3×
“We compare reconstructions using the Plug-and- Play priors framework by experimenting with six different denoising techniques/priors -K-SVD [4], BM3D [5], PLOW [7], Total Variation (TV) [21], q-GGMRF [22] and discrete reconstruction (DR) [23].”
The Split Bregman Method for L1-Regularized Problems
Goldstein, T., & Osher, S. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080725891 · Cited by 4,282 · cited 3×
“Examples of new methods include a wide variety of patch based non-local means approaches [3], generalizations of bi-lateral filtering approaches [1], patch-based dictionary learning methods such as K-SVD [4], block-matching with transform-based denoising such as BM3D [5], and a variety of total-variation [2], and Mark…”
Fast Image Recovery Using Variable Splitting and Constrained Optimization
Afonso, M. V., Bioucas-Dias, J. M., & Figueiredo, M. A. T. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2047910 · Cited by 1,223 · cited 3×
“In order to design an algorithm for (3) that decouples the forward and prior terms, we first split the variable x into two new variables x and v, and reformulate equation (3) as the following constrained optimization problem [15].”
InfluentialMR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning
Ravishankar, S., & Bresler, Y. (2011) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2010.2090538 · Cited by 1,059 · cited 2×
“Model-based reconstruction is a powerful framework for solving a variety of inverse problems in imaging including denoising, deblurring, tomographic reconstruction, and MRI reconstruction.”
Cited by
Items 301–400 of 1,000
Blind image deblurring using class-adapted image priors
Ljubenović, M., & Figueiredo, M. A. T. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296329 · Cited by 23
“The method is based on the so-called plug-andplay approach, recently proposed in [16].”
Efficient blind deblurring under high noise levels
Anger, J., Delbracio, M., & Facciolo, G. (2019) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2019.8868661 · Cited by 22
“Generic frameworks such as Plug-and-Play priors [18] and more recently Regularization by Denoising [19], allow to use any image denoiser as a prior for restoration problems.”
Liu, X., Chen, Y., Peng, Z., & Wu, J. (2019) · Sensors · doi:10.3390/s19235139 · Cited by 20
The Neural Tangent Link Between CNN Denoisers and Non-Local Filters
Tachella, J. A., Tang, J., & Davies, M. E. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00851 · Cited by 33
Li, Y., Jiang, Y., Zhang, H., Liu, J., Ding, X., & Gui, G. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.01.041 · Cited by 20
Hwang, S., 韓, 昌., Venkatakrishnan, S. V., Bouman, C. A., & Ortalan, V. (2017) · Measurement Science and Technology · doi:10.1088/1361-6501/aa57df · Cited by 20
Self-citationPositive Sparse Signal Denoising: What Does a CNN Learn?
Al-Shabili, A., & Selesnick, I. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3160372 · Cited by 19
A Relaxed Proximal Gradient Descent Algorithm for Convergent Plug-and-Play with Proximal Denoiser
Hurault, S., Chambolle, A., Leclaire, A., & Papadakis, N. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31975-4_29 · Cited by 26
PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
Gan, W., Zhai, Q., McCann, M. T., García–Cardona, C., Kamilov, U. S., & Wohlberg, B. E. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3375276 · Cited by 19
Self-citationDegradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising
Zeng, H., Feng, K., Zhao, X., Cao, J., Huang, S., Luong, H. Q., & Philips, W. R. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3543920 · Cited by 24
Neural Networks and Deep Learning
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.024 · Cited by 19
Dual Forward-Backward Unfolded Network for Flexible Plug-and-Play
Repetti, A., Terris, M., Wiaux, Y., & Pesquet, J.-C. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909564 · Cited by 19
PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent
Fermanian, R., Pendu, M. L., & Guillemot, C. M. (2023) · SIAM Journal on Imaging Sciences · doi:10.1137/22m1490843 · Cited by 24
“The method in [55] uses the ADMM algorithm [5] which iteratively and alternately solves two sub-problems, each associated to either the regularization term or the data fidelity term.”
Shi, B., Li, D., Wang, Y., Su, Y., & Lian, Q. (2023) · Signal Processing · doi:10.1016/j.sigpro.2023.109236 · Cited by 19
Convolutional Sparse Representations with Gradient Penalties
Wohlberg, B. E. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462151 · Cited by 19
Self-citationAcceleration of RED via vector extrapolation
Hong, T., Romano, Y., & Elad, M. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102575 · Cited by 20
Hyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps
Wang, Z., Zhuang, L., Gao, L., Marinoni, A., Zhang, B., & Ng, M. K. (2020) · Remote Sensing · doi:10.3390/rs12244117 · Cited by 22
“Plug and play technique is a flexible framework that allows imaging models to be combined with state-of-the-art priors or denoising models [37].”
Gan, W., Ying, C., Boroojeni, P. E., Wang, T., Eldeniz, C., Hu, Y., Liu, J., Chen, Y., An, H., & Kamilov, U. S. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3304475 · Cited by 21
Mixed Noise-Oriented Hyperspectral and Multispectral Image Fusion
Fu, X., Liang, H., & Jia, S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3323480 · Cited by 26
A Complex Quasi-Newton Proximal Method for Image Reconstruction in Compressed Sensing MRI
Hong, T., Hernández-García, L., & Fessler, J. A. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3369404 · Cited by 22
“…e.g., total variation (TV) [1], wavelets [2], and transform-learning [3] etc. Recently, more advanced priors or frameworks were introduced for CS MRI reconstruction, such as low-rank [4], plug and play [5], [6], model-based deep learning [7], score-based generative models [8], to name a few.”
Wu, Z., Huang, C., & Zeng, T. (2024) · SIAM Journal on Imaging Sciences · doi:10.1137/23m1611166 · Cited by 25
DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model
Pan, Z., Zeng, H., Cao, J., Zhang, K., & Chen, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02390 · Cited by 29
Xu, S., Hammernik, K., Lingg, A., Kübler, J., Krumm, P., Rueckert, D., Gatidis, S., & Küstner, T. (2024) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2024.102475 · Cited by 20
Dar, Y., Elad, M., & Bruckstein, A. M. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2871388 · Cited by 17
“Here we establish a practical method addressing the optimization problem in (10) based on the alternating direction method of multipliers (ADMM) approach [10] (for additional uses see, e.g., [11], [12], [14], [16], [30]).”
Time-frequency-masking-based Determined BSS with Application to Sparse IVA
Yatabe, K., & Kitamura, D. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682217 · Cited by 18
“Such idea of replacing a proximity operator is called plug-and-play method [19] which is attracting many researchers recently [20–23].”
SAR image despeckling using plug‐and‐play ADMM
Baraha, S., & Sahoo, A. K. (2020) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2019.0609 · Cited by 18
Joint ptycho-tomography with deep generative priors
Aslan, S., Liu, Z., Nikitin, V., Biçer, T., Leyffer, S., & Gürsoy, D. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ac1d35 · Cited by 18
“[49] proposed the PNP framework, which enables integrating implicit priors for denoising, to enable use of iterative optimization methods.”
Learning Spectral-Spatial Prior Via 3DDNCNN for Hyperspectral Image Deconvolution
Wang, X., Chen, J., Richard, C., & Brie, D. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054539 · Cited by 22
“Within this framework, various methods have been proposed based on the ADMM [13] or the half quadratic splitting method [14] to solve a variety of 2D image inverse problems like denoising, deblurring and superresolution [15–18].”
2-Step Sparse-View CT Reconstruction with a Domain-Specific Perceptual NetworkPreprint
Wei, H., Schiffers, F., Würfl, T., Shen, D., Kim, D. J., Katsaggelos, A. K., & Cossairt, O. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04743 · Cited by 21
“[42], referred to Plug-and-Play (P&P)-priors and can be combined with learned denoising.”
Model-based deep learning enables time-resolved computational microscopy
Gao, Y., & Cao, L. (2026) · PhotoniX · doi:10.1186/s43074-025-00222-2 · Cited by 18
“Plug-and-play methods provide a promising solution that elegantly integrates physical models and data priors learned by deep neural networks [97, 98].”
The Power Of Triply Complementary Priors For Image Compressive Sensing
Zha, Z., Yuan, X., Zhou, J. T., Zhou, J., Wen, B., & Zhu, C. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190707 · Cited by 17
“Deep Plug-And-Play Methods: Recent works on the plug-and-play (PnP) framework [21, 26, 27] allowed applying the effective image denoiser to solve the general inverse problems, such as image deblurring [21], image inpainting [28] and computational imaging [29], etc.”
Bayesian Inversion for Nonlinear Imaging Models Using Deep Generative Priors
Bohra, P., Pham, T.-A., Dong, J., & Unser, M. A. (2022) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3236155 · Cited by 17
“The plug-and-play priors (PnP) [37] and regularizationby-denoising (RED) [38] frameworks are two successful examples that provide a way to carry out this integration.”
Dual Alternating Direction Method of Multipliers for Inverse Imaging
Song, L., Ge, Z., & Lam, E. Y. M. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3167915 · Cited by 17
Tuning-Free Plug-and-Play Hyperspectral Image Deconvolution With Deep Priors
Wang, X., Chen, J., & Richard, C. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3253549 · Cited by 22
“Applications include magnetic resonance imaging (MRI) reconstruction [19], [20], 2-D image restoration [21], [22], [23], [24], and”
Nonlocal low-rank plus deep denoising prior for robust image compressed sensing reconstruction
Li, Y., Gao, L., Hu, B., Gui, G., & Chen, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120456 · Cited by 18
Wu, P., Ding, M., & Zheng, Y. (2023) · IET Intelligent Transport Systems · doi:10.1049/itr2.12383 · Cited by 17
Fast and Reliable Score-Based Generative Model for Parallel MRI
Hou, R., Li, F., & Zeng, T. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3333538 · Cited by 17
FSPnP: Plug-and-Play Frequency–Spatial-Domain Hybrid Denoiser for Thermal Infrared Image
He, Y., Zhang, C., Zhang, B., & Chen, Z. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3343794 · Cited by 17
Score-based Diffusion Models for Photoacoustic Tomography Image Reconstruction
Dey, S., Saha, S., Feng, B. T., Cui, M., Delisle, L., Leong, O., Wang, L. V., & Bouman, K. L. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447579 · Cited by 22
Convergent Plug-and-Play with Proximal Denoiser and Unconstrained Regularization Parameter
Hurault, S., Chambolle, A., Leclaire, A., & Papadakis, N. (2024) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-024-01195-w · Cited by 32
“Plug-and-Play (PnP) [10] and Regularization by Denoising (RED) [6] methods consist in splitting algorithms in which the descent step on the regularization function is performed by an off-the-shelf image denoiser.”
Fast Controllable Diffusion Models for Undersampled MRI Reconstruction
Jiang, W., Xiong, Z., Liu, F., Ye, N., & Sun, H. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635891 · Cited by 23
Deep Model-Based Super-Resolution with Non-uniform Blur
Laroche, C., Almansa, A., & Tassano, M. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00184 · Cited by 24
Compressive sensing of ECG signals using plug-and-play regularization
Unni, V. S., Gavaskar, R. G., & Chaudhury, K. N. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108738 · Cited by 17
“In the original work [19], the PnP scheme was explored for a different proximal algorithm – ADMM – but it was adapted to PGD in [20].”
HIONet: Deep priors based deep unfolded network for phase retrieval
Yang, Y., Lian, Q., Zhang, X., Zhang, D., & Zhang, H. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103797 · Cited by 17
PPR: Plug-and-play regularization model for solving nonlinear imaging inverse problems
Shi, B., Lian, Q., & Fan, X. (2019) · Signal Processing · doi:10.1016/j.sigpro.2019.04.013 · Cited by 18
4D X-Ray CT Reconstruction using Multi-Slice Fusion
Majee, S., Balke, T., Kemp, C. A. J., Buzzard, G. T., & Bouman, C. A. (2019) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2019.8747328 · Cited by 17
Self-citationGhani, M. U., & Karl, W. C. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00486 · Cited by 18
SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimizationPreprint
Driggs, D., Tang, J., Liang, J., Davies, M. E., & Schönlieb, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12266 · Cited by 17
White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?Preprint
Yu, Y., Buchanan, S., Pai, D., Chu, T., Wu, Z., Tong, S., Bai, H., Zhai, Y., Haeffele, B. D., & Ma, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.13110 · Cited by 21
Deep-blur: Blind identification and deblurring with convolutional neural networks
Debarnot, V., & Weiss, P. O. (2024) · Biological Imaging · doi:10.1017/s2633903x24000096 · Cited by 19
Plug and play augmented HQS: Convergence analysis and its application in MRI reconstruction
Rasti-Meymandi, A., Ghaffari, A., & Fatemizadeh, E. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.061 · Cited by 19
Array SAR 3-D Sparse Imaging Based on Regularization by Denoising Under Few Observed Data
Wang, Y., Zhan, X., Gao, J., Yao, J., Wei, S., & Bai, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3406711 · Cited by 20
“Venkatakrishnan et al . first proposed a reconstruction framework based on PnP, which effectively improves the quality of magnetic resonance images (MRI) [34].”
Multi-Scale Energy (MuSE) Framework for Inverse Problems in Imaging
Chand, J. R., & Jacob, M. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3449101 · Cited by 16
“For example, the Plug-and-Play (PnP) methods [4]–[6] replace the proximal map in the above algorithms with a pre-learned Convolutional Neural Network (CNN)- based denoiser.”
Deep Internal Learning: Deep learning from a single input
Tirer, T., Giryes, R., Chun, S. Y., & Eldar, Y. C. (2024) · IEEE Signal Processing Magazine · doi:10.1109/msp.2024.3385950 · Cited by 16
Learning-Based Image Reconstruction via Parallel Proximal Algorithm
Bostan, E., Kamilov, U. S., & Waller, L. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2833812 · Cited by 16
“One class of the algorithms called “plug-and-play” (PnP) [12]–[17] replaces the proximal step with powerful denoising techniques such as BM3D [18].”
Learning a Probabilistic Strategy for Computational Imaging Sensor Selection
Sun, H., Dalca, A. V., & Bouman, K. L. (2020) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccp48838.2020.9105133 · Cited by 16
ADMM-Inspired Reconstruction Network for Compressive Spectral Imaging
Sogabe, Y., Sugimoto, S., Kurozumi, T., & Kimata, H. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190998 · Cited by 17
“The substitution can be explained by using the principles of Plug-and-Play (PnP) priors [12].”
Efficient $\ell ^0$ Gradient-Based Super-Resolution for Simplified Image Segmentation
Cascarano, P., Calatroni, L., & Piccolomini, E. L. (2021) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2021.3070720 · Cited by 18
Joint Deblurring and Denoising of THz Time-Domain Images
Ljubenović, M., Zhuang, L., Beenhouwer, J. D., & Sijbers, J. (2020) · IEEE Access · doi:10.1109/access.2020.3045605 · Cited by 16
Augmented NETT regularization of inverse problems
Obmann, D., Nguyen, L. V., Schwab, J., & Haltmeier, M. (2021) · Journal of Physics Communications · doi:10.1088/2399-6528/ac26aa · Cited by 16
“In particular, ADMM inspired plug-andplay priors [9,38,44] may be most closely related.”
Blind image deconvolution via salient edge selection and mean curvature regularization
Ge, X., Tan, J., Zhang, L., & Qian, Y. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108336 · Cited by 18
Random mesh projectors for inverse problemsPreprint
Gupta, S., Kothari, K., de Hoop, M. V., & Dokmanić, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11718 · Cited by 18
“These are further related to the notion of plug-and-play regularization (Venkatakrishnan et al. (2013)), as well as early uses of neural nets to unroll and adapt standard sparse reconstruction algorithms (Gregor and LeCun (2010); Xin et al. (2016)).”
Li, Y., Qiu, D., & Zhang, X. (2023) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2023.3254156 · Cited by 15
Multiple Complementary Priors for Multispectral Image Compressive Sensing Reconstruction
Zha, Z., Wen, B., Yuan, X., Zhang, J., Zhou, J., Jiang, X., & Zhu, C. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3251730 · Cited by 15
“Moreover, in contrast to the PnP framework that only uses pretrained models [38], [39], [44], [46], [56], the proposed H-PnP framework not only uses the pretrained model but also adaptively learns and tests images by using nonlocal modeling.”
Algorithms in Tomography and Related Inverse Problems—A Review
Tassiopoulou, S., Κούκιου, Γ., & Anastassopoulos, V. (2024) · Algorithms · doi:10.3390/a17020071 · Cited by 15
Zero-shot reconstruction of ocean sound speed field tensors: A deep plug-and-play approach
Li, S., Cheng, L., Fu, X., & Li, J. (2024) · The Journal of the Acoustical Society of America · doi:10.1121/10.0026125 · Cited by 15
Sharpening Hyperspectral Images Using Plug-and-Play Priors
Teodoro, A. M., Bioucas‐Dias, J. M., & Figueiredo, M. A. T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-53547-0_37 · Cited by 15
A relaxed Newton–Picard like method for Huber variant of total variation based image restoration
Zhang, J. (2019) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2019.02.021 · Cited by 16
Deep recursive network for image denoising with global non-linear smoothness constraint prior
Wang, C., Ren, C., He, X., & Qing, L. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.09.070 · Cited by 16
High-Resolution ISAR Imaging Based on Plug-and-Play 2D ADMM-Net
Li, X., Bai, X., Yujie, Z., & Zhou, F. (2022) · Remote Sensing · doi:10.3390/rs14040901 · Cited by 15
Quantum Denoising-Based Super-Resolution Algorithm Applied to Dental Tomography Images
Dutta, S., Tuador, N. K., Michetti, J., Georgeot, B., Pham, D.-H., Basarab, A., & Kouamé, D. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761623 · Cited by 15
Uncertainty Quantification When Learning Dynamical Models and Solvers With Variational Methods
Lafon, N., Fablet, R., & Naveau, P. (2023) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2022ms003446 · Cited by 16
WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution
Altekrüger, F., & Hertrich, J. (2023) · SIAM Journal on Imaging Sciences · doi:10.1137/22m1496542 · Cited by 19
The Foundations of Computational Imaging: A signal processing perspective
Karl, W. C., Fowler, J. E., Bouman, C. A., Çetin, M., Wohlberg, B. E., & Ye, J. C. (2023) · IEEE Signal Processing Magazine · doi:10.1109/msp.2023.3274328 · Cited by 15
“A particularly impactful and popular approach has been plug-and-play priors (PPPs) [39], [40], which was motivated by the advances in image denoising within the image processing community.”
Self-citation∇-Prox: Differentiable Proximal Algorithm Modeling for Large-Scale Optimization
Lai, Z., Wei, K., Fu, Y., Härtel, P., & Heide, F. (2023) · ACM Transactions on Graphics · doi:10.1145/3592144 · Cited by 20
“In practice, researchers often employ a mixture of several regularizers, which is what we assume in our example problem where 𝜆 ≥ 0, 𝑔 (· ; 𝜃 𝑟 ) denotes an image prior implicitly modeled in an off-the-shelf denoiser ( a.k.a. Plug-and-Play prior [Venkatakrishnan et al. 2013]).”
InfluentialLocal Kernels That Approximate Bayesian Regularization and Proximal Operators
Ong, F., Milanfar, P., & Getreuer, P. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2893071 · Cited by 15
“Approaches such as [17] have become popular for suggesting an ad hoc procedure for replacing the proximal operators with simpler (often patch-based) denoisers.”
Lagerwerf, M. J., Pelt, D. M., Palenstijn, W. J., & Batenburg, K. J. (2020) · Journal of Imaging · doi:10.3390/jimaging6120135 · Cited by 16
Unsupervised Image Restoration Using Partially Linear Denoisers
Ke, R., & Schönlieb, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3070382 · Cited by 15
Denoising Score-Matching for Uncertainty Quantification in Inverse ProblemsPreprint
Ramzi, Z., Remy, B., Lanusse, F., Starck, J., & Ciuciu, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08698 · Cited by 23
“Plug-and-Play Priors The idea of using a denoising model as a prior for inverse problems solving was introduced by Venkatakrishnan et al. [2013] who used non-learned denoisers to replace the proximity operator in the ADMM algorithm [Boyd, 2011].”
Joint image restoration and edge detection in cooperative game formulation
Yang, C., Wang, W., & Feng, X. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108363 · Cited by 14
A Novel Reconstruction Algorithm with High Performance for Compressed Ultrafast Imaging
Shen, Q., Tian, J., & Pei, C. (2022) · Sensors · doi:10.3390/s22197372 · Cited by 14
Equilibrium Image Denoising With Implicit Differentiation
Chen, Q., Wang, Y., Geng, Z., Wang, Y., Yang, J., & Lin, Z. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3255104 · Cited by 15
“…fundamental problem in low level vision, image denoising has been extensively studied for many years; however, it is still a research hotspot because denoising can be adopted by many other image restoration problems as a building block [1], [2], [3], [4], which further broadens its applicability.”
Tensor completion via convolutional sparse coding with small samples-based training
Liao, T., Wu, Z., Chen, C., Zheng, Z., & Zhang, X. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109624 · Cited by 14
Izzatullah, M., Alkhalifah, T. A., Romero, J., Corrales, M., Luiken, N., & Ravasi, M. (2023) · Geophysics · doi:10.1190/geo2023-0035.1 · Cited by 14
Dynamic proximal unrolling network for compressive imaging
Yang, Y., Tao, R., Wei, K., & Fu, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.08.034 · Cited by 15
Deformation-Compensated Learning for Image Reconstruction Without Ground Truth
Gan, W., Sun, Y., Eldeniz, C., Liu, J., An, H., & Kamilov, U. S. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3163018 · Cited by 16
“For example, plug-and-play priors (PnP) [35] and regularization by denoisers (RED) [36] refer to a related family”
Blind Restoration of Atmospheric Turbulence-Degraded Images Based on Curriculum Learning
Jie, S., Xie, C., & Gao, Z. (2022) · Remote Sensing · doi:10.3390/rs14194797 · Cited by 15
Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach
Goyes-Peñafiel, P., Vargas, E., Correa, C. V., Sun, Y., Kamilov, U. S., Wohlberg, B. E., & Argüello, H. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3290468 · Cited by 14
Self-citationYoung, S. I., Dalca, A. V., Ferrante, E., Golland, P., Metzler, C. A., Fischl, B. R., & Iglesias, J. E. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3299789 · Cited by 15
“Closely related to RED is the older “plug-and-play priors” method [29], [30], which uses a denoising step in place of the denoising optimzation in RED.”
Generative Plug and Play: Posterior Sampling for Inverse Problems
Bouman, C. A., & Buzzard, G. T. (2023) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton58177.2023.10313413 · Cited by 14
“Over the past decade, Plug-and-Play (PnP) [1, 2] has become a popular method for reconstructing images using a modular framework consisting of a forward and prior model.”
Self-citationNF-ULA: Normalizing Flow-Based Unadjusted Langevin Algorithm for Imaging Inverse Problems
Cai, Z., Tang, J., Mukherjee, S., Li, J., Schönlieb, C., & Zhang, X. (2024) · SIAM Journal on Imaging Sciences · doi:10.1137/23m1581807 · Cited by 21
“In a more general case where the prior p(x) is not available in closed form, the authors of [56] propose a plug-and-play (PnP) denoising-based approach for learning the prior [84,96].”
InfluentialDesigning stable neural networks using convex analysis and ODEs
Sherry, F., Celledoni, E., Ehrhardt, M. J., Murari, D., Owren, B., & Schönlieb, C. (2024) · Physica D Nonlinear Phenomena · doi:10.1016/j.physd.2024.134159 · Cited by 22
Optimized Pre-Compensating Compression
Dar, Y., Elad, M., & Bruckstein, A. M. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2845125 · Cited by 14
“in the Plug-and-Play Priors method [8] for image restoration, where an optimization stage corresponding to a Maximum A-Posteriori (MAP) Gaussian denoising problem is replaced with the application of an existing denoiser (such as BM3D [30]).”
A Novel Plug-and-Play SAR Reconstruction Framework Using Deep Priors
Alver, M. B., Saleem, A., & Çetin, M. (2019) · IEEE Radar Conference (RadarConf) · doi:10.1109/radar.2019.8835598 · Cited by 14
An inner-loop free solution to inverse problems using deep neural networks
Fai, K., Wei, Q., Carin, L., & Heller, K. (2017) · neural information processing systems · Cited by 13
Deep Hyperspectral and Multispectral Image Fusion With Inter-Image Variability
Wang, X., Borsoi, R. A., Richard, C., & Chen, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3273118 · Cited by 19
Nonconvex Rician noise removal via convergent plug-and-play framework
Wei, D., Weng, S., & Li, F. (2023) · Applied Mathematical Modelling · doi:10.1016/j.apm.2023.06.033 · Cited by 16
DDRM-PR: Fourier phase retrieval using denoising diffusion restoration models
Kaya, M. O., & Öktem, F. S. (2025) · Applied Optics · doi:10.1364/ao.545150 · Cited by 13
Fourier synthesis optical diffraction tomography for kilohertz rate volumetric imaging
Brown, P. T., Jabbarzadeh, N., Meneses, L., Swanson, K., Pintuff, A., Monakhova, E., Kruithoff, R., Wadhwa, N., Galati, D. F., & Shepherd, D. P. (2025) · Science Advances · doi:10.1126/sciadv.adr8004 · Cited by 13
Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
Wang, H., Zhang, T., Yu, M., Sun, J., Ye, W., Wang, C., & Zhang, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58601-0_27 · Cited by 14
“(3) can be solved via the following iterative scheme, (5) The first step only depends on the choice of a forward model, while the second step only depends on the choice of prior and can be interpreted as a denoising operation [27].”
Metadata
- Authors
- Venkatakrishnan, S. V., Bouman, C. A., & Wohlberg, B.
- Affiliations
- Purdue University West Lafayette (US)
- Los Alamos National Laboratory (US)
- Venue
- 2013 IEEE Global Conference on Signal and Information Processing
- Publisher
- IEEE
- Published
- 2013-12
- Pages
- 945-948
- ISSN
- 2376-4066 (ISSN-L)
- OpenAlex
- W2087416986
- Cited by
- 1,178
- References
- 32
- Citations by year
- 2026: 99 · 2025: 172 · 2024: 147 · 2023: 177 · 2022: 121 · 2021: 182 · 2020: 102 · 2019: 75 · 2018: 52 · 2017: 24 · 2016: 16 · 2015: 8 · 2014: 2
- FWCI
- 5.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Global Conference on Signal and Information Processing (publishedVersion)
- Purdue e-Pubs (Purdue University System) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Mathematics › Mathematical Physics › Numerical methods in inverse problems
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Medical Imaging Techniques and Applications
- Keywords
- plug-and-play priors, model-based reconstruction, image denoising, imaging inverse problems, X-ray CT, electron microscopy, magnetic resonance imaging, ultrasonography, prior models, software integration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.