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 501–600 of 1,000
Model-Based Reconstruction with Learning: From Unsupervised to Supervised and Beyond
Huang, Z., Ye, S., McCann, M. T., & Ravishankar, S. (2023) · Cambridge University Press eBooks · doi:10.1017/9781009042529.005 · Cited by 9
Denoising Generalized Expectation-Consistent Approximation for MR Image Recovery
Shastri, S. K., Ahmad, R., Metzler, C. A., & Schniter, P. (2022) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2022.3207109 · Cited by 9
“[21] to propose that the prox in (4b) be replaced by a high-performance image denoiser f 2 : R N → RN like BM3D [41], giving rise to PnP-ADMM.”
Deep CNN denoiser prior for blurred images restoration with multiplicative noise
Li, Y., Hu, S., Ni, G., & Zeng, T. (2023) · Inverse Problems and Imaging · doi:10.3934/ipi.2022075 · Cited by 9
CTIS-GAN: computed tomography imaging spectrometry based on a generative adversarial network
Wu, L., & Cai, W. (2023) · Applied Optics · doi:10.1364/ao.478230 · Cited by 9
Low-Light Image Enhancement via Implicit Priors Regularized Illumination Optimization
Ma, Q., Wang, Y., & Zeng, T. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3323835 · Cited by 11
Projected Multi-Agent Consensus Equilibrium (PMACE) With Application to Ptychography
Zhai, Q., Buzzard, G. T., Mertes, K. M., Wohlberg, B. E., & Bouman, C. A. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3328288 · Cited by 9
Self-citationRegularization by Denoising: Bayesian Model and Langevin-Within-Split Gibbs Sampling
Faye, E. C., Fall, M. D., & Nicolas Dobigeon, B. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3520012 · Cited by 16
“…regularization based on the same DRUNet denoiser; • RED-HQS: HQS algorithm with RED regularization based on the same DRUNet denoiser; • PnP-ADMM [5]: ADMM with a PnP regularization based on the same DRUNet denoiser; • PnP-ULA [22]: ULA with a PnP regularization based on the same DRUNet…”
Regularization by denoising sub-sampled Newton method for spectral CT multi-material decomposition
Perelli, A., & Andersen, M. S. (2021) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2020.0191 · Cited by 9
“In imaging applications where the input prior is difficult to model, powerful regularization techniques are based on data-driven models or by exploiting denoising functions, like the Plug-and-Play (PnP) approach [39] or the regularization by denoising (RED) [40–42].”
Revisit dictionary learning for video compressive sensing under the Plug-and-Play framework
Yang, Q., & Zhao, Y. (2022) · Asia Pacific Conference on Optics Manufacture and International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM) · doi:10.1117/12.2624208 · Cited by 9
“Thanks to the PnP framework, 15–17 now various denoisers can be used in an in-situ manner.”
MemXCT: Design, Optimization, Scaling, and Reproducibility of X-Ray Tomography Imaging
Hidayetoğlu, M., Biçer, T., de Gonzalo, S. G., Ren, B., Gürsoy, D., Kettimuthu, R., Foster, I. T., & Hwu, W. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3128032 · Cited by 9
Li, S., Kang, T., Wu, J., Chen, W., Lin, Q. M., Wu, Z., Wang, J., Cai, C., & Cai, S. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acfb71 · Cited by 8
Wavenumber-aware diffusion sampling to regularize multiparameter elastic full waveform inversion
Taufik, M. H., & Alkhalifah, T. A. (2024) · Geophysical Journal International · doi:10.1093/gji/ggae437 · Cited by 8
Zhang, D., Lian, Q., Su, Y., & Ren, T. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123390 · Cited by 8
“Besides, the pretrained DRUNet model [27] was adopted as the deep prior agent.”
InfluentialSparse graph-regularized dictionary learning for full waveform inversion
Fu, H., Qi, H., Dong, S., & Hua, R. (2023) · Computers & Geosciences · doi:10.1016/j.cageo.2023.105449 · Cited by 8
Discovering Structure From Corruption for Unsupervised Image Reconstruction
Leong, O., Gao, A. F., Sun, H., & Bouman, K. L. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3325752 · Cited by 12
Video Super-Resolution Using Plug-and-Play Priors
Zerva, M. C., & Kondi, L. P. (2024) · IEEE Access · doi:10.1109/access.2024.3355195 · Cited by 9
“Initially introduced by Venkatakrishnan et al. [42], PPP has garnered significant attention across various domains of computer vision and image processing.”
InfluentialConstrained Plug-and-Play Priors for Image Restoration
Benfenati, A., & Cascarano, P. (2024) · Journal of Imaging · doi:10.3390/jimaging10020050 · Cited by 8
Adaptive total variational regularization of Gaussian denoisers for multiplicative noise removal
Shi, K. (2024) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2024.06.017 · Cited by 8
NG-RED:Nonconvex group-matrix residual denoising learning for image restoration
Li, Y., Wu, H., Jiang, X., & Ding, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125876 · Cited by 8
Deep plug-and-play HIO approach for phase retrieval
Işıl, Ç., & Öktem, F. S. (2025) · Applied Optics · doi:10.1364/ao.545152 · Cited by 12
PALADIN: a novel plug-and-play 3D CS-MRI reconstruction method
Wu, J., Yin, S.-B., Jiang, T.-X., Liu, G., & Zhao, X.-L. (2025) · Inverse Problems · doi:10.1088/1361-6420/adb8c6 · Cited by 9
“Another potential way is the plug-and-play (PnP) framework [29, 47, 62], which offers flexibility by incorporating off-the-shelf denoising algorithms (denoisers) for solving various image inverse problems.”
CurvPnP: Plug-and-play blind image restoration with deep curvature denoiser
Li, Y., Chang, H., & Duan, Y. (2025) · Signal Processing · doi:10.1016/j.sigpro.2025.109951 · Cited by 12
Stability of data-dependent ridge-regularization for inverse problems
Neumayer, S., & Altekrüger, F. (2025) · Inverse Problems · doi:10.1088/1361-6420/adda74 · Cited by 8
“…data (a common setting for medical imaging or material sciences), namely with • the total variation (TV) regularizer [51] as a well-known and widely used convex baseline; • the Prox-DRUNet [24, 25] as one of the best-performing methods for convergent plug-and-play image-reconstruction [20, 58, 60].”
Deep Equilibrium Models for Poisson Imaging Inverse Problems via Mirror Descent
Daniele, C., Villa, S., Vaiter, S., & Calatroni, L. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m1779048 · Cited by 13
Towards optimal algorithms for the recovery of low-dimensional models with linear rates
Traonmilin, Y., Aujol, J., & Guennec, A. (2026) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2026.101936 · Cited by 8
AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling
Guo, B., Han, Y., & Wen, J. (2019) · neural information processing systems · Cited by 8
Solving RED With Weighted Proximal Methods
Hong, T., Yavneh, I., & Zibulevsky, M. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.2979062 · Cited by 8
“Following this path, several authors proposed a general framework, called Plug-and-Play Priors (P (3)) [16], [17], for using the abundance of high-performance image denoisers as priors for other inverse problems.”
D-VDAMP: Denoising-Based Approximate Message Passing for Compressive MRI
Metzler, C. A., & Wetzstein, G. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414708 · Cited by 8
“P&P ADMM and RED are both run for 200 iterations.”
InfluentialEdge-guided CNN for Denoising Images from Portable Ultrasound Devices
Ma, Y., Yang, F., & Basu, A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412758 · Cited by 11
“Model-based methods generally require repeated iterations to solve this formula, while discriminative learning methods learn the prior parameter θ through a loss function [25] [26] as below: Combining the two methods here, the regularization term [27] [28] corresponds to a denoising sub-problem.”
Plug-and-Play video super-resolution using edge-preserving filtering
Ghassab, V. K., & Bouguila, N. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103359 · Cited by 8
A Trainable Bounded Denoiser Using Double Tight Frame Network for Snapshot Compressive Imaging
Shi, B., Wang, Y., & Lian, Q. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746236 · Cited by 8
Xu, W., Zhou, Y., Liu, D., Wang, X., & Chen, W. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3166029 · Cited by 10
On the Convergence of Non-Convex Phase Retrieval With Denoising Priors
Xue, D., Zheng, Z., Dai, W., Li, C., Zou, J., & Xiong, H. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3203228 · Cited by 8
Machine Learning for MRI Reconstruction
Hammernik, K., Küstner, T., & Rueckert, D. (2022) · Advances in magnetic resonance technology and applications · doi:10.1016/b978-0-12-822726-8.00021-x · Cited by 12
Gao, M., Fessler, J. A., & Chan, H. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad0eb4 · Cited by 8
Proximal Nested Sampling with Data-Driven Priors for Physical Scientists
McEwen, J. D., Liaudat, T. I., Price, M. A., Cai, X., & Pereyra, M. (2023) · International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (MaxEnt) · doi:10.3390/psf2023009013 · Cited by 8
PyProximal - scalable convex optimization in Python
Ravasi, M., Örnhag, M. V., Luiken, N., Leblanc, O., & Uruñuela, E. (2024) · The Journal of Open Source Software · doi:10.21105/joss.06326 · Cited by 8
Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems
Buskulic, N., Fadili, J. M., & Quéau, Y. (2024) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-024-01191-0 · Cited by 8
CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping
Xu, X., Gan, W., Kothapalli, S. V. V. N., Yablonskiy, D. A., & Kamilov, U. S. (2025) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-025-01236-y · Cited by 8
“PnP [36, 37] is a widely-used framework that extend the traditional DL by enabling the integration of the physical measurement models and powerful CNN denoisers as image priors to provide state-of-the-art reconstruction algorithms (see recent reviews of PnP in [38, 39]).”
Generative priors for MRI reconstruction trained from magnitude-only images using phase augmentation
Luo, G., Wang, X., Blumenthal, M., Schilling, M., Kotikalapudi, R., Rauf, E. H. U., Focke, N. K. N., & Uecker, M. (2025) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2024.0323 · Cited by 8
“0061.”
Optically coherent image reconstruction in the presence of phase errors using advanced-prior models
Spencer, M. F., Pellizzari, C. J., & Bouman, C. A. (2018) · doi:10.1117/12.2304692 · Cited by 8
“Here, N(μ,C) indicates a real-valued normal distribution with mean μ and covariance matrix C.(14,15) The denoising operator, G, is mathematically equivalent to computing the MAP estimate of x from the noisy image, r+u, corrupted by Gaussian noise.”
Self-citationAutomatic foreground extraction from imperfect backgrounds using multi-agent consensus equilibrium
Wang, X., Juang, J., & Chan, S. H. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.102907 · Cited by 8
“Such algorithm is known as the Plugand-Play ADMM [62], [63], [65] (and variations thereafter [60], [66]).”
Patch-Based Image Restoration Using Expectation Propagation
Yao, D., McLaughlin, S., & Altmann, Y. (2022) · SIAM Journal on Imaging Sciences · doi:10.1137/21m1427541 · Cited by 8
Xie, M., Liu, J., Sun, Y., Gan, W., Wohlberg, B. E., & Kamilov, U. S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00448 · Cited by 8
“Despite the recent popularity of PnP/RED, current PnP/RED algorithms assume exact knowledge of the measurement operator, limiting their ability to solve problems involving parametric uncertainties in the data acquisition.”
InfluentialSelf-citationLi, H., Zhao, X.-L., Lin, J., & Chen, Y. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3136217 · Cited by 8
Monotonically Convergent Regularization by Denoising
Hu, Y., Liu, J., Xu, X., & Kamilov, U. S. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897639 · Cited by 9
“One of the earliest methods is plug-and-play priors (PnP) [4], which proposed to extend the traditional proximal optimization [14] by replacing the proximal operator with a more general denoiser.”
SINCO: A Novel Structural Regularizer for Image Compression Using Implicit Neural Representations
Gao, H., Gan, W., Sun, Z., & Kamilov, U. S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095531 · Cited by 8
A general framework for denoising phaseless diffraction measurementsPreprint
Chang, H., & Marchesini, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01417 · Cited by 8
“Moreover, similar to the work in [61], [51], [52], some advanced filters as BM3D can be introduced to replace the variational image denoising methods.”
Teodoro, A. M., Bioucas‐Dias, J. M., & Figueiredo, M. A. T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.00605 · Cited by 8
“The PnP approach replaces the proximity operator with some black-box denoiser [6], [7], the key advantage being that the same denoiser can be used for different problems, since its use is fully decoupled from the particularities of the inverse problem being addressed.”
InfluentialTFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging ProblemsPreprint
Wei, K., Avilés-Rivero, A. I., Liang, J., Fu, Y., Huang, H., & Schönlieb, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.05703 · Cited by 34
“Plug-and-play (PnP) Techniques The definitional concept of PnP was first introduced in (Danielyan et al., 2010; Zoran and Weiss, 2011; Venkatakrishnan et al., 2013).”
InfluentialDoDo: Double DOE Optical System for Multishot Spectral Imaging
Urrea, S., Jácome, R., Asif, M. S., Argüello, H., & García, H. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3402320 · Cited by 7
FedPnP: Personalized graph-structured federated learning
Rasti-Meymandi, A., Sajedi, A., & Plataniotis, K. N. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111455 · Cited by 9
Deep Guess acceleration for explainable image reconstruction in sparse-view CT
Piccolomini, E. L., Evangelista, D., & Morotti, E. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102530 · Cited by 7
Progressive plug and play full waveform inversion with multitask learning
Zhang, B., & Wang, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-04506-2 · Cited by 7
Li, G., Sheng, L., Duan, B., Li, Y., Hei, D., & Xing, Q. (2024) · Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment · doi:10.1016/j.nima.2024.169130 · Cited by 7
Deep Plug-and-Play Algorithm for Unsaturated Imaging
Bacca, J., Monroy, B., & Argüello, H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446495 · Cited by 7
Lei, J., Liu, Q., & Wang, X. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108617 · Cited by 7
Seismic Reservoir Characterization With Implicit Neural Representations
Romero, J., Heidrich, W., Luiken, N., & Ravasi, M. (2024) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000275 · Cited by 7
Fast and Robust Phase Retrieval via Deep Expectation-Consistent Approximation
Shastri, S. K., & Schniter, P. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3527140 · Cited by 7
“For example, the plug-and-play (PnP) [28] and RED [29], [30] frameworks have been adapted to PR in [20], [31], [32].”
A review on the development of 3D image reconstruction algorithms based on sparse single-photon data
Zhu, Y., Yu, C., Yang, Y., Pan, Q., & Shuai, Y. (2025) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2025.109148 · Cited by 7
Convexity in ReLU Neural Networks: Beyond ICNNs?
Gagneux, A., Massias, M., Soubies, E., & Gribonval, R. (2025) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-025-01253-x · Cited by 7
LoFi: Neural Local Fields for Scalable Image Reconstruction
Khorashadizadeh, A., Liaudat, T. I., Liu, T., McEwen, J. D., & Dokmanić, I. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3594983 · Cited by 7
“Unsupervised methods based on deep generative models [31], [75], [76], [77], [78] and plug-and-play (PnP) [79], [80], [81] show strong performance on various image reconstruction tasks.”
Survey of Deep Learning and Physics-Based Approaches in Computational Wave Imaging
Lin, Y., Feng, S., Theiler, J. P., Chen, Y., Villa, U., Rao, J., Greenhall, J., Pantea, C., Anastasio, M. A., & Wohlberg, B. E. (2025) · Proceedings of the IEEE · doi:10.1109/jproc.2026.3684003 · Cited by 7
“The PPP framework, initially developed in the computational imaging community [95], [96], [97], provides a flexible and powerful approach for solving inverse problems by integrating advanced image denoisers into iterative optimization algorithms.”
Self-citationPlug-and-Play Prior Based on Gaussian Mixture Model Learning for Image Restoration in Sensor Network
Shi, M., & Feng, L. (2018) · IEEE Access · doi:10.1109/access.2018.2884795 · Cited by 7
Learning Plug-And-Play Proximal Quasi-Newton Denoisers
Al-Shabili, A., Mansour, H., & Boufounos, P. T. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054537 · Cited by 7
Study on Convergence of Plug-and-Play ISTA With Adaptive-Kernel Denoisers
Liu, T., Xing, L., & Sun, Z. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3111594 · Cited by 7
Sketched RT3D: How to Reconstruct Billions of Photons Per Second
Tachella, J. A., Sheehan, M. P., & Davies, M. E. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746304 · Cited by 7
Plug-and-Play-Based Algorithm for Mixed Noise Removal with the Logarithm Norm Approximation Model
Liu, J., Wu, J., Xu, M., & Huang, Y. (2022) · Mathematics · doi:10.3390/math10203810 · Cited by 7
Super-resolution image reconstruction from sparsity regularization and deep residual-learned priors
Zhong, X., Liang, N., Cai, A., Yu, X., Li, L., & Yan, B. (2023) · Journal of X-Ray Science and Technology · doi:10.3233/xst-221299 · Cited by 8
Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
Hurault, S., Kamilov, U. S., Leclaire, A., & Papadakis, N. (2023) · HAL · doi:10.48550/arxiv.2306.03466 · Cited by 12
A Generally Regularized Inversion for NMR Applications and Beyond
Lin, E., Chen, B., Ni, Z., Huang, Y., Yang, Y., & Chen, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3277972 · Cited by 7
“In the future, GRIN could be enhanced by incorporating non-model-based prior knowledge, such as Plug-and-Play priors [51], [52], [53], which impose regularizations using off-the-shelf denoise algorithms or data-driven neural networks.”
Data-Driven Mirror Descent with Input-Convex Neural Networks
Tan, H. Y., Mukherjee, S., Tang, J., & Schönlieb, C. (2023) · SIAM Journal on Mathematics of Data Science · doi:10.1137/22m1508613 · Cited by 8
“in 2013 were able to achieve fast and robust convergence for tomography problems [26].”
Combining Deep Image Prior and Second-Order Generalized Total Variance for Image Denoising
Xu, J., You, S., Guo, Y., & Fan, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3292158 · Cited by 7
Learned interferometric imaging for the SPIDER instrument
Mars, M., Betcke, M. M., & McEwen, J. D. (2023) · RAS Techniques and Instruments · doi:10.1093/rasti/rzad054 · Cited by 7
“These methods typically adopt plug-and-play (PnP) denoisers that are used instead of a proximal update step (Venkatakrishnan et al. 2013; Ryu et al. 2019).”
Learning Sparsity-Promoting Regularizers Using Bilevel Optimization
Ghosh, A., McCann, M. T., Mitchell, M., & Ravishankar, S. (2024) · SIAM Journal on Imaging Sciences · doi:10.1137/22m1506547 · Cited by 7
Xue, Z., Yang, F., Gao, J., Chen, Z., Peng, H., Zou, C., Jin, H. M., & Hu, C. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3524717 · Cited by 7
SBM3D: Sparse Regularization Model Induced by BM3D for Weighted Diffraction Imaging
Shi, B., Lian, Q., Chen, S., & Fan, X. (2018) · IEEE Access · doi:10.1109/access.2018.2865997 · Cited by 7
An Iterative Denoising and Backwards Projections Method and its Advantages for Blind Deblurring
Tirer, T., & Giryes, R. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451723 · Cited by 7
Energy Dissipation with Plug-and-Play Priors
Sommerhoff, H., Kolb, A., & Moeller, M. (2019) · Cited by 7
Image Restoration Based on End-to-End Unrolled Network
Tao, X., Zhou, H., & Chen, Y. (2021) · Photonics · doi:10.3390/photonics8090376 · Cited by 7
“Therefore, hybrid IR methods under unrolled framework were proposed [50,51].”
Gan, W., Hu, Y., Eldeniz, C., Liu, J., Chen, Y., An, H., & Kamilov, U. S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00450 · Cited by 7
Al-Shabili, A., Xu, X., Selesnick, I., & Kamilov, U. S. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897933 · Cited by 7
Deep Network Series for Large-Scale High-Dynamic Range Imaging
Aghabiglou, A., Terris, M., Jackson, A., & Wiaux, Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094843 · Cited by 7
Boosting with fine-tuning for deep image denoising
Xie, Z., Liu, L., Wang, C., & Chen, Z. (2023) · Signal Processing · doi:10.1016/j.sigpro.2023.109356 · Cited by 7
Investigating Customization Strategies and Convergence Behaviors of Task-Specific ADMM
Liu, R., Mu, P., & Zhang, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3113796 · Cited by 7
Robustness of Deep Equilibrium Architectures to Changes in the Measurement Model
Hu, J., Shoushtari, S., Zou, Z., Liu, J., Sun, Z., & Kamilov, U. S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096199 · Cited by 7
“PnP and RED are two well-known frameworks that specify image priors using image denoisers trained to remove additive white Gaussian noise (AWGN) in the first category [5–7].”
Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfittingPreprint
Sun, Z., Sanchez, T., Latorre, F., & Cevher, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01748 · Cited by 7
Plug‐and‐play algorithms for convex non‐convex regularization: Convergence analysis and applications
Xu, Y., Qu, M., Liu, L., Liu, G., & Zou, J. X. (2023) · Mathematical Methods in the Applied Sciences · doi:10.1002/mma.9710 · Cited by 6
“The earliest PnP algorithm can be traced back to [38], which utilized a generic denoiser to replace the proximal operator in ADMM and yielded the PnP-ADMM algorithm.”
Seismic data reconstruction via a hybrid convolutional neural network-low-rank method
Gao, W., Fu, L., Fang, W., Wu, J., & Wang, Y. (2024) · Geophysics · doi:10.1190/geo2024-0195.1 · Cited by 6
Radio Map Estimation via Latent-Domain Plug-and-Play Denoisers
Xu, L., Cheng, L., Chen, J., Pu, W., & Fu, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889056 · Cited by 6
“Our idea is to use the plug-and-play (PnP) framework from computational imaging [17], [18].”
Sun, Y., Li, S., Fang, S., Cheng, L., Li, J., & Gerstoft, P. (2025) · The Journal of the Acoustical Society of America · doi:10.1121/10.0036641 · Cited by 7
Plug-and-Play Priors as a Score-Based Method
Park, C. Y., Hu, Y., McCann, M. T., García–Cardona, C., Wohlberg, B. E., & Kamilov, U. S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084503 · Cited by 14
“For example, the popular PnP-ADMM [2,3] algorithm is obtained by replacing prox γh in ADMM with a more general image denoiser, D σ , resulting in the iterates Algorithm 1 PnP-ADMM with score-based denoising 3: ( c, t ) ← param _ matching ( σ k ) 4: where σ ≥ 0 controls the denoising strength.”
Self-citationAn explicit conditioning method for image reconstruction in electrical capacitance tomography
Taylor, S. H., & Garimella, S. V. (2015) · Flow Measurement and Instrumentation · doi:10.1016/j.flowmeasinst.2015.10.009 · Cited by 6
Sparse Matrix-Based HPC Tomography
Marchesini, S., Trivedi, A., Enfedaque, P., Perciano, T., & Parkinson, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50371-0_18 · Cited by 6
A Plug-and-Play Deep Denoiser Prior Model for Accelerated MRI Reconstruction
Karaoğlu, H. H., & Ekşioğlu, E. M. (2022) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp55681.2022.9851376 · Cited by 6
Colibazzi, F., Lazzaro, D., Morigi, S., & Samorè, A. (2023) · Inverse Problems and Imaging · doi:10.3934/ipi.2023014 · Cited by 11
van Gogh, S., Mukherjee, S., Rawlik, M., Pereira, A., Spindler, S., Zdora, M., Stauber, M., Varga, Z., & Stampanoni, M. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3325442 · Cited by 6
“In recent years the concept of data-driven regularization has been gaining popularity and, in the context of alternating schemes, Plug-and-Play-like denoising has received a lot of attention due to its astonishing performance [21], [22], [23], [24].”
Imaging privacy threats from an ambient light sensor
Liu, Y., Wornell, G. W., Freeman, W. T., & Durand, F. (2024) · Science Advances · doi:10.1126/sciadv.adj3608 · Cited by 6
“…x k + 1 + u k ) on the signal prior domain and can be viewed as a denoising problem without explicitly expressing R(·), that is where ‖ ‖ is a denoising function with the noisy signal v and the noise level σ as inputs and ̂ σ k = λ∕ρ is the estimated noise standard deviation (SD) in each iteration.”
High Dynamic Range Modulo Imaging for Robust Object Detection in Autonomous Driving
Contreras, K., Monroy, B., & Bacca, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91767-7_12 · Cited by 6
Low-rank tensor recovery via jointing the non-convex regularization and deep prior
Liu, Q., Ge, H., & Su, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130610 · Cited by 6
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.