The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Plug-and-Play priors for model based reconstruction
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 101–200 of 1,000
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
Garber, T., & Tirer, T. (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/cvpr52733.2024.02385 · Cited by 123
“A successful choice of such pretrained DNNs are Gaussian denoisers, as was initially demonstrated in different “plug-and-play” (PnP) and “regularization by de-noising” (RED) iterative schemes [25, 36, 40, 44].”
Triply Complementary Priors for Image Restoration
Zha, Z., Wen, B., Yuan, X., Zhou, J. T., Zhou, J., & Zhu, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3086049 · Cited by 73
“Recent works on the PnP framework [11], [45]–[49] allowed applying the effective image denoiser to solve the general inverse problems, such as image deblurring [11], image inpainting [50] and computational imaging [46], etc.”
Postprocessing of Compressed Images via Sequential Denoising
Dar, Y., Bruckstein, A. M., Elad, M., & Giryes, R. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2558825 · Cited by 73
Eigen-CNN: Eigenimages Plus Eigennoise Level Maps Guided Network for Hyperspectral Image Denoising
Zhuang, L., Ng, M. K., Gao, L., & Wang, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3379199 · Cited by 88
SNIPS: Solving Noisy Inverse Problems StochasticallyPreprint
Kawar, B., Vaksman, G., & Elad, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14951 · Cited by 150
Deep plug-and-play prior for hyperspectral image restoration
Lai, Z., Wei, K., & Fu, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.057 · Cited by 85
Deep Spatial-Angular Regularization for Light Field Imaging, Denoising, and Super-Resolution
Guo, M., Hou, J., Jin, J., Chen, J., & Chau, L. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3087485 · Cited by 73
“(3) can be decoupled into two sub-problems correspondingly for the data likelihood term and the regularization term [46], [47]:”
Liu, D., Li, J., Yuan, Q., Li, Z., He, J., Zhao, S., & Xiao, Y. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.01.018 · Cited by 70
BM3D-PRGAMP: Compressive phase retrieval based on BM3D denoising
Metzler, C. A., Maleki, A., & Baraniuk, R. G. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532810 · Cited by 70
Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspective
Chan, S. H. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2892123 · Cited by 78
Shen, H., Jiang, M., Li, J., Zhou, C., Yuan, Q., & Zhang, L. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3135954 · Cited by 72
Untrained networks for compressive lensless photography
Monakhova, K., Tran, V., Kuo, G., & Waller, L. (2021) · Optics Express · doi:10.1364/oe.424075 · Cited by 68
Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
Bhat, G., Danelljan, M., Yu, F., Gool, L. V., & Timofte, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00246 · Cited by 69
Liu, Y.-Y., Zhao, X.-L., Zheng, Y., Ma, T.-H., & Zhang, H. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3045169 · Cited by 81
A review on Single Image Super Resolution techniques using generative adversarial network
Singla, K., Pandey, R., & Ghanekar, U. (2022) · Optik · doi:10.1016/j.ijleo.2022.169607 · Cited by 70
Halimi, A., Maccarone, A., Lamb, R. A., Buller, G. S., & McLaughlin, S. (2021) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2021.3111572 · Cited by 67
“Note that the resulting depth updates alternates between robust to outliers non-linear parameter estimation (line 11) and a filtering step (line 12), which are commonly observed steps in several state-of-the-art algorithms [22], [24], [25] and optimization algorithms [49].”
Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning
Tirer, T., & Giryes, R. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2920250 · Cited by 64
“While we have adapted the IDBP framework [26] to SR (the original IDBP work did not consider this setup), one may apply the proposed strategy in this work to the schemes in [20,29,34] as well.”
InfluentialLin, C.-H., & Bioucas‐Dias, J. M. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2953808 · Cited by 65
GAN-Based Projector for Faster Recovery With Convergence Guarantees in Linear Inverse Problems
Raj, A., Li, Y., & Bresler, Y. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00570 · Cited by 63
Plug-and-Play Synthetic Aperture Radar Image Formation Using Deep Priors
Alver, M. B., Saleem, A., & Çetin, M. (2020) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2020.3047473 · Cited by 64
“Different denoisers have been adopted within the PnP framework, such as BM3D [46] (as in [6], [20], [22]–[24], [27], [28], [30], [39]), non-local means (NLM, as in [22], [24], [33], [36], [42]), NCSR [47] (as in [21]), Gaussian mixture models (GMM, as in [25], [29], [32]), and deep learning based…”
InfluentialDeep iterative reconstruction for phase retrieval
Işıl, Ç., Öktem, F. S., & Koç, A. (2019) · Applied Optics · doi:10.1364/ao.58.005422 · Cited by 67
“This is the main idea in plug-and-play regularization [28, 29].”
Compressive Imaging: Structure, Sampling, Learning
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447 · Cited by 93
Reconstructive spectrometers: hardware miniaturization and computational reconstruction
Zhang, Y., Yang, E.-B., Yoon, H. H., Cheng, Q., Sun, Z., Hasan, T., & Cai, W. (2025) · eLight · doi:10.1186/s43593-025-00101-0 · Cited by 60
“In addition, due to the scarcity of large-scale spectral datasets, small-data learning theory [120] and the unfolded networks, also known as the plug-and-play framework [121–123], may also provide important directions for future development of spectral reconstruction techniques [124, 125].”
Masuyama, Y., Yatabe, K., Koizumi, Y., Oikawa, Y., & Harada, N. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682744 · Cited by 67
Plug in estimation in high dimensional linear inverse problems a rigorous analysis *
Fletcher, A. K., Pandit, P., Rangan, S., Sarkar, S., & Schniter, P. (2019) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ab321a · Cited by 67
Total Deep Variation: A Stable Regularization Method for Inverse Problems
Kobler, E., Effland, A., Kunisch, K. K., & Pock, T. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3124086 · Cited by 69
“A related and practically very fruitful idea, known as plug-and-play prior [17] or regularization by denoising [18], is the replacement of the regularizer (or an associated proximal operator) by an existing denoising algorithm such as BM3D [19].”
Back-Projection Based Fidelity Term for Ill-Posed Linear Inverse Problems
Tirer, T., & Giryes, R. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2988779 · Cited by 58
“framework [18] is inspired by the plug-and-play priors concept [42], which encourages the usage of existing Gaussian denoisers as “black boxes” to implicitly dictate the prior s(x̃) when solving inverse problems.”
SIMBA: Scalable Inversion in Optical Tomography Using Deep Denoising Priors
Wu, Z., Sun, Y., Matlock, A. C., Liu, J., Tian, L., & Kamilov, U. S. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2999820 · Cited by 58
“Recently, a new class of methods, called plug-and-play priors (PnP) [9], have popularized the idea of”
Adaptive Hyperspectral Mixed Noise Removal
Jiang, T.-X., Zhuang, L., Huang, T., Zhao, X.-L., & Bioucas‐Dias, J. M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3085779 · Cited by 60
Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey
Xia, W., Shan, H., Wang, G., & Zhang, Y. (2023) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3204407 · Cited by 57
“The idea of introducing auxiliary variables is in the same spirit of plug-and-play (PnP) [22, 23], which can decouple the primal problem and inverse conveniently.”
A Neural-Network-Based Convex Regularizer for Inverse Problems
Goujon, A., Neumayer, S., Bohra, P., Ducotterd, S., & Unser, M. A. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3306100 · Cited by 84
“A remedy for some of these issues is provided by the convolutional-neural-network (CNN) variants of the plug-andplay (PnP) framework [16], [17], [18], [19].”
Bi-l 0 -l 2 -norm regularization for blind motion deblurring
Shao, W., Li, H., & Elad, M. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.08.017 · Cited by 55
Convolutional proximal neural networks and Plug-and-Play algorithms
Hertrich, J., Neumayer, S., & Steidl, G. (2021) · Linear Algebra and its Applications · doi:10.1016/j.laa.2021.09.004 · Cited by 72
“This technique is meanwhile known as Plug-and-Play (PnP) algorithms [49, 56] and led to improved results in certain applications, e.g., [10, 22, 35, 40, 53].”
Deep Non-Local Kalman Network for Video Compression Artifact Reduction
Lu, G. S., Zhang, X., Ouyang, W., Xu, D., Chen, L., & Gao, Z. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2943214 · Cited by 59
“Venkatakrishnan et al. [37] built on the ADMM [38] algorithm and proposed to replace the proximal operator of the regularizer with a denoiser such as BM3D [39], which motivates subsequent works to learn the proximal operator using CNNs [34], [35].”
Score-Based Generative ClassifiersPreprint
Zimmermann, R. S., Schott, L., Song, Y., Dunn, B. A., & Klindt, D. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00473 · Cited by 66
“Previous work has suggested the effectiveness of these diffusion-based models for out-of-domain (OOD) tasks such as adversarially robust classification [51] and as a general prior for natural images [48, 19].”
Fully Trainable and Interpretable Non-local Sparse Models for Image Restoration
Lecouat, B., Ponce, J., & Mairal, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_15 · Cited by 53
“mproximalgradientdescentinorderto solveaconstrainedoptimizationproblemfordenoising;[6]optimizehyperparametersofnonlinearreaction diffusionmodels;[3]unrollaninteriorpointalgorithm. Finally,Plug-and-Play[47]isaframeworkforimage restorationexploitingadenoisingpriorasamodularpartofmodel-basedoptimizationmethodstosolve vari…”
Fixed-Point and Objective Convergence of Plug-and-Play Algorithms
Nair, P., Gavaskar, R. G., & Chaudhury, K. N. (2021) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2021.3066053 · Cited by 53
“In particular, PnP using NLM-type denoisers is known to produce promising image reconstructions [9], [34]– [41].”
DeepInverse: A Python package for solving imaging inverse problems with deep learning
Tachella, J. A., Terris, M., Hurault, S., Wang, A., Davy, L., Scanvic, J., Sechaud, V., Vo, R., Moreau, T., Davies, T., et al. (2025) · The Journal of Open Source Software · doi:10.21105/joss.08923 · Cited by 71
“Denoising Plug-and-Play Priors Plug-and-Play (PnP) methods replace the proximal operator [33] or the gradient [34] of the regularizer g with a pretrained denoiser, often based on deep learning.”
Low-rank tensor completion via combined non-local self-similarity and low-rank regularization
Li, X., Zhao, X.-L., Jiang, T.-X., Zheng, Y., Ji, T.-Y., & Huang, T. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.07.092 · Cited by 52
“Recently, the Plug and Play framework has become a hot topic, which is first proposed by Venkatakrishnan et al. [53] .”
2.5D Deep Learning For CT Image Reconstruction Using A Multi-GPU Implementation
Ziabari, A., Ye, D. H., Srivastava, S., Sauer, K. D., Thibault, J., & Bouman, C. A. (2018) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2018.8645364 · Cited by 61
Self-citationLightweight FISTA-Inspired Sparse Reconstruction Network for mmW 3-D Holography
Wang, M., Wei, S., Liang, J., Liu, S., Shi, J., & Zhang, X. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3093307 · Cited by 51
“Moreover, many other sophisticated regularizers are explored, such as group sparsity [27], Cauchy-based penalty [28], and even plug-and-play (PnP) priors technique [29].”
Genzel, M., März, M., & Seidel, R. J. (2021) · Information and Inference A Journal of the IMA · doi:10.1093/imaiai/iaab001 · Cited by 49
Theoretical Perspectives on Deep Learning Methods in Inverse Problems
Scarlett, J., Heckel, R., Rodrigues, M. R. D., Hand, P., & Eldar, Y. C. (2022) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2023.3241123 · Cited by 49
Regularising Inverse Problems with Generative Machine Learning Models
Duff, M., Campbell, N. D. F., & Ehrhardt, M. J. (2023) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-023-01162-x · Cited by 49
Shen, H., & Zhang, L. (2023) · Science China Earth Sciences · doi:10.1007/s11430-022-9999-9 · Cited by 54
A Majorize-Minimize Framework for Rician and Non-Central Chi MR Images
Varadarajan, D., & Haldar, J. P. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2015.2427157 · Cited by 50
“4Note that other popular denoising methods such as non-local means (NLM) [53] are also easily incorporated into our MM framework using the regularization frameworks described in [54], [55].”
UNO: Unlimited Sampling Meets One-Bit Quantization
Eamaz, A., Mishra, K. V., Yeganegi, F., & Soltanalian, M. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3356253 · Cited by 47
“When the input signal is contaminated with additive noise, we apply the recently introduced new plug-and-play (PnP) priors [63] to the alternating direction method of multipliers (ADMM) as an additional reconstruction algorithm step.”
InfluentialImage denoising for real‐time MRI
Klosowski, J., & Frahm, J. (2016) · Magnetic Resonance in Medicine · doi:10.1002/mrm.26205 · Cited by 47
Ada-LISTA: Learned Solvers Adaptive to Varying Models
Aberdam, A., Golts, A., & Elad, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3125041 · Cited by 47
“An alternative to the above is incorporating LISTA as a fixed black-box denoiser, and merging it within the plug-and-play (Venkatakrishnan et al., 2013) or RED (Romano et al.”
Plug-and-Play ISTA Converges With Kernel Denoisers
Gavaskar, R. G., & Chaudhury, K. N. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.2986643 · Cited by 47
“A natural question thus is can we exploit the excellent denoising capability of NLM and BM3D for regularization purpose? One such approach leads to the so-called Plug-and-Play (PnP) method [7], [8].”
Full waveform inversion by proximal Newton method using adaptive regularization
Aghamiry, H. S., Gholami, A., & Operto, S. (2020) · Geophysical Journal International · doi:10.1093/gji/ggaa434 · Cited by 47
“Such an adaptive regularization has been applied to linear inverse problems in, e.g., Danielyan et al. (2011) and Venkatakrishnan et al. (2013).”
Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
Holden, M., Pereyra, M., & Zygalakis, K. C. (2022) · SIAM Journal on Imaging Sciences · doi:10.1137/21m1406313 · Cited by 47
Unified Single-Image and Video Super-Resolution via Denoising Algorithms
Brifman, A., Romano, Y., & Elad, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2924173 · Cited by 47
“l is to formulate the two problems in a unified way, and derive a single algorithm that can serve them both. The key to the formation of such a bridge is the use of the Plug-and-PlayPrior (PPP) method [27], and the more recent framework of Regularization-by-Denoising (RED) [28]. Both PPP and RED offer a path for turnin…”
InfluentialDeep-Learned Regularization and Proximal Operator for Image Compressive Sensing
Chen, Z., Guo, W., Feng, Y., Li, Y., Zhao, C., Ren, Y. C., & Shao, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3088611 · Cited by 45
Deep Sparse Representation Based Image Restoration With Denoising Prior
Xu, W., Zhu, Q., Qi, N., & Chen, D. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3170689 · Cited by 48
Scene-Adapted plug-and-play algorithm with convergence guarantees
Teodoro, A. M., Bioucas‐Dias, J. M., & Figueiredo, M. A. T. (2017) · Machine learning for signal processing ... · doi:10.1109/mlsp.2017.8168194 · Cited by 44
“The PnP framework [7] emerges from noticing that sub-problems (7)-(8) can be interpreted as the MAP solutions to pure denoising problems.”
MAPEM-Net: an unrolled neural network for Fully 3D PET image reconstruction
Gong, K., Wu, D., Kim, K., Yang, J., Sun, T., Fakhri, G. E., Seo, Y., & Li, Q. (2019) · International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine (Fully3D) · doi:10.1117/12.2534904 · Cited by 44
Deep Griffin–Lim Iteration: Trainable Iterative Phase Reconstruction Using Neural Network
Masuyama, Y., Yatabe, K., Koizumi, Y., Oikawa, Y., & Harada, N. (2021) · IEEE Journal on Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3034486 · Cited by 32
Hy-Demosaicing: Hyperspectral Blind Reconstruction From Spectral Subsampling
Zhuang, L., Ng, M. K., Fu, X., & Bioucas‐Dias, J. M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3102136 · Cited by 45
Self-Supervised Deep Unrolled Reconstruction Using Regularization by Denoising
Huang, P., Zhang, C., Zhang, X., Li, X., Liang, D., & Ying, L. L. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3332614 · Cited by 47
“As many denoising algorithms have demonstrated their success in the past years, several methods have been proposed to leverage denoising algorithms in image reconstruction [38], [39].”
Regularized Fourier Ptychography Using an Online Plug-and-play Algorithm
Sun, Y., Xu, S., Li, Y., Tian, L., Wohlberg, B. E., & Kamilov, U. S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683057 · Cited by 43
“Recently, the effectiveness of PnP was extended beyond the original ADMM formulation [12] to other proximal algorithms such as primal-dual splitting and PGM [20–22].”
InfluentialSelf-citationEMnet: an unrolled deep neural network for PET image reconstruction
Gong, K., Wu, D., Li, Q., Kim, K., Yang, J., Fakhri, G. E., & Seo, Y. (2019) · SPIE Medical Imaging: Physics of Medical Imaging · doi:10.1117/12.2513096 · Cited by 43
Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging
Wu, Z., Yang, C., Su, X., & Yuan, X. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01777-y · Cited by 43
“Fortunately, the Plug-and-Play (PnP) framework [5,32,34,37] provides a feasible way to develop an efficient and flexible algorithm for video SCI reconstruction, especially for large-scale problems under the framework of alternating direction method of multipliers (ADMM) [3] or generalized alternating projection (GAP)…”
Stochastic Image Denoising by Sampling from the Posterior Distribution
Kawar, B., Vaksman, G., & Elad, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00213 · Cited by 42
“Adopting a broader view, the fact that MMSE denoisers can be leveraged for different tasks is a fascinating phenomenon, which has already been exposed in recent work in different contexts [46, 35, 23].”
Thin On-Sensor Nanophotonic Array Cameras
Chakravarthula, P., Sun, J., Li, X., Lei, C., Chou, G., Bijelic, M., Fröch, J. E., Majumdar, A., & Heide, F. (2023) · ACM Transactions on Graphics · doi:10.1145/3618398 · Cited by 42
Deep class-aware image denoising
Remez, T., Litany, O., Giryes, R., & Bronstein, A. M. (2017) · International Conference on Sampling Theory and Applications · doi:10.1109/sampta.2017.8024474 · Cited by 42
Hyder, R., Shah, V., Hegde, C., & Asif, M. S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682811 · Cited by 42
Gates-Controlled Deep Unfolding Network for Image Compressed Sensing
Li, T., Yan, Q., Zou, Q., & Dai, Q. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3354423 · Cited by 41
“From a Bayesian perspective, Venkatakrishnan et al. [30] replace the proximity operator with animagedenoiserwhichbuildsabridgebetweenproximalmeth-odsanddeepimagemodels.”
Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
González, M., Almansa, A., & Tan, P. (2022) · SIAM Journal on Imaging Sciences · doi:10.1137/21m140225x · Cited by 41
Blind Image Deblurring Using a Non-Linear Channel Prior Based on Dark and Bright Channels
Ge, X., Tan, J., & Zhang, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3101154 · Cited by 43
Equivariant Plug-and-Play Image Reconstruction
Terris, M., Moreau, T., Pustelnik, N., & Tachella, J. A. (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/cvpr52733.2024.02386 · Cited by 62
Song, S., Dai, Y., Song, Y., & Jin, T. (2024) · IEEE Transactions on Microwave Theory and Techniques · doi:10.1109/tmtt.2024.3479189 · Cited by 44
“The plug-and-play framework is a popular radar image denoiser [38].”
Parameter-free Plug-and-Play ADMM for image restoration
Wang, X., & Chan, S. H. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952371 · Cited by 40
Light Field Super-Resolution Using Edge-Preserved Graph-Based Regularization
Ghassab, V. K., & Bouguila, N. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2946094 · Cited by 40
“The algorithm which is going to be used in this section is an extention of the conventional ADMM [24], [39] which would be able to resolve our problem efficiently.”
On Plug-and-Play Regularization Using Linear Denoisers
Gavaskar, R. G., Athalye, C. D., & Chaudhury, K. N. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3075092 · Cited by 40
“PnP-FISTA was first introduced in [19], while PnP-ADMM was introduced in [23].”
Bilevel Methods for Image Reconstruction
Crockett, C., & Fessler, J. A. (2022) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000111 · Cited by 55
Event-Driven Video Frame Synthesis
Wang, Z. W., Jiang, W., He, K. F., Shi, B., Katsaggelos, A. K., & Cossairt, O. S. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00532 · Cited by 39
“, the plug & play [39] and the onetime denoising.”
High dynamic range and super-resolution from raw image bursts
Lecouat, B., Eboli, T., Ponce, J., & Mairal, J. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530180 · Cited by 43
“Following the plug-and-play strategy [Venkatakrishnan et al. 2013] which has proven powerful in the signal processing literature, we replace the proximal operator 𝐺 above by a function 𝐺 𝜔 represented by a CNN and parameterized by 𝜔 , such that the update (10) becomes where 𝛾 is also a…”
Provable General Bounded Denoisers for Snapshot Compressive Imaging With Convergence Guarantee
Shi, B., Wang, Y., & Li, D. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3241551 · Cited by 38
“See https://www.ieee.org/publications/rights/index.html for more information. deep priors via deep denoisers [8], [37].”
Denoising: a powerful building block for imaging, inverse problems and machine learning
Milanfar, P., & Delbracio, M. (2025) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2024.0326 · Cited by 54
“Iterative Shrinkage/Thresholding (IST) algorithms [60, 57, 61, 62, 63] utilize the shrinkage/thresholding function (Moreau proximal mapping) derived from the regularizer R [62] to solve optimization problems.”
Machine learning for image reconstruction
Hammernik, K., & Knöll, F. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-816176-0.00007-7 · Cited by 40
CPGD: Cadzow Plug-and-Play Gradient Descent for Generalised FRI
Simeoni, M., Besson, A., Hurley, P., & Vetterli, M. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3041089 · Cited by 37
“Such an approach is reminiscent of the plug-and-play (PnP) framework [28], [29] from image processing, which leverages generic denoisers to approximate complex proximal operators [27].”
Mani, M., Magnotta, V. A., & Jacob, M. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28756 · Cited by 38
Determined BSS Based on Time-Frequency Masking and Its Application to Harmonic Vector Analysis
Yatabe, K., & Kitamura, D. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3073863 · Cited by 37
“The above heuristic generalization of the proposed algo-rithm is closely related to the plug-and-play scheme [49].”
Deep RED Unfolding Network for Image Restoration
Kong, S., Wang, W., Feng, X., & Jia, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3136623 · Cited by 44
Truncated Residual Based Plug-and-Play ADMM Algorithm for MRI Reconstruction
Hou, R., Li, F., & Zhang, G. (2022) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2022.3145187 · Cited by 37
Deep and Low-Rank Quaternion Priors for Color Image Processing
Xu, T., Kong, X., Shen, Q., Chen, Y., & Zhou, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3233589 · Cited by 37
Deep Equilibrium Models for Snapshot Compressive Imaging
Zhao, Y., Zheng, S., & Yuan, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25475 · Cited by 37
“…in-The Thirty-Seventh AAAI Conference on Artificial Intelligence ( AAAI-23 AAAI-23 ) telligence Inspired by the plug-and-play (PnP) framework (Venkatakrishnan, Bouman, and Wohlberg 2013; Sreehari et al. 2016) which has been proposed for inverse problems with provable convergence (Chan, Wang,…”
CSI-PPPNet: A One-Sided One-for-All Deep Learning Framework for Massive MIMO CSI Feedback
Chen, W. R., Wan, W., Wang, S., Sun, P., Li, G. Y., & Ai, B. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3342735 · Cited by 37
Deep Residual Learning for Model-Based Iterative CT Reconstruction Using Plug-and-Play Framework
Ye, D. H., Srivastava, S., Thibault, J., Sauer, K. D., & Bouman, C. A. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461408 · Cited by 36
“To tackle this challenge, we use the Plug-and-Play (PnP) framework [8, 9] which utilizes alternating direction method of multipliers (ADMM) [10, 11] for the MBIR optimization.”
Self-citationImage Restoration and Reconstruction using Targeted Plug-and-Play Priors
Teodoro, A. M., Bioucas‐Dias, J. M., & Figueiredo, M. A. T. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2914773 · Cited by 41
“[11] proposed a framework that leverages the advances in image denoising to solve other inverse problems, such as image deblurring, compressive imaging, super-resolution, among others.”
InfluentialBaraha, S., Sahoo, A. K., & Modalavalasa, S. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108521 · Cited by 36
Provable Probabilistic Imaging Using Score-Based Generative Priors
Sun, Y., Wu, Z., Chen, Y., Feng, B. T., & Bouman, K. L. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3449114 · Cited by 69
“Inspired by the connection between proximal operator and MAP denoiser, PnP [3], [4] emerged as a pioneering approach for imposing expressive yet implicit image priors through de-noising.”
Multi-Resolution Data Fusion for Super-Resolution Electron Microscopy
Sreehari, S., Venkatakrishnan, S. V., Bouman, K. L., Simmons, J. P., Drummy, L. F., & Bouman, C. A. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.146 · Cited by 36
“The key step in our solution is to use our library-based non-local means (LB-NLM) denoising filter as a prior model within the P&P framework [21, 25] – to produce visually true textures and edge features in image interpolations, while significantly reducing mean squared error and artifacts such as “jaggies”.”
Self-citationIdentifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
Xia, Z., & Chakrabarti, A. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093586 · Cited by 35
“In addition to its practical utility in improving the quality of photographs taken in low-light or by cheaper sensors, image denoisers can be used as generic “plug-and-play” priors within iterative approaches to solve a larger variety of generic image restoration tasks (e.g., [1, 4, 23, 29]).”
A Plug-and-Play Deep Image Prior
Sun, Z., Latorre, F., Sanchez, T., & Cevher, V. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414879 · Cited by 35
PatchNR: learning from very few images by patch normalizing flow regularization
Altekrüger, F., Denker, A., Hagemann, P., Hertrich, J., Maaß, P., & Steidl, G. (2023) · Inverse Problems · doi:10.1088/1361-6420/acce5e · Cited by 35
Learned Factor Graphs for Inference From Stationary Time Sequences
Shlezinger, N., Farsad, N., Eldar, Y. C., & Goldsmith, A. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3139506 · Cited by 30
SGD-Net: Efficient Model-Based Deep Learning With Theoretical Guarantees
Liu, J., Sun, Y., Gan, W., Xu, X., Wohlberg, B. E., & Kamilov, U. S. (2021) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2021.3085534 · Cited by 42
“The key idea in PnP is to replace the proximal operator with an advanced image denoiser H σ , where σ > 0 controls the strength of denoising.”
InfluentialSelf-citationLucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts
Lecouat, B., Ponce, J., & Mairal, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00237 · Cited by 49
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.