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 801–900 of 1,000
Provably Convergent Data-Driven Convex-Nonconvex RegularizationPreprint
Shumaylov, Z., Budd, J., Mukherjee, S., & Schönlieb, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.05812 · Cited by 7
Reducing artifacts of intra-frame video coding via sequential denoising
Dar, Y., Bruckstein, A. M., Elad, M., & Giryes, R. (2016) · IEEE Convention of Electrical and Electronics Engineers in Israel · doi:10.1109/icsee.2016.7806177 · Cited by 2
“Similar to [4] and [9], we develop an iterative algorithm for the solution of (3).”
Image Deconvolution Using Mixed-Order Salient Edge Selection
Hu, D., Tan, J., & Ge, X. (2023) · Circuits Systems and Signal Processing · doi:10.1007/s00034-022-02283-1 · Cited by 2
“Nevertheless, we can treat the noise as a separate step before performing image deblurring as suggested in the literature [11, 40, 47], where Fig.”
Self-Supervised Image Denoising Using Implicit Deep Denoiser Prior
Lin, H., Zhuang, Y., Ding, X., Zeng, D., Huang, Y., Tu, X., & Paisley, J. W. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25245 · Cited by 2
Image Denoisers in Tomography: Enhancing Quality of Bimodal Imaging for Corrosion Studies
Zhan, Q., Shakoorioskooie, M., Mannes, D. C., & Kaestner, A. P. (2024) · e-Journal of Nondestructive Testing · doi:10.58286/29248 · Cited by 2
Miao, 黎. L., Lingqiang, 张. Z., Xi, 王. W., Chenyan, 王. W., Chaorui, 陈. C., Zhaohui, 郭. G., & Xueyin, 赵. Z. (2024) · Acta Optica Sinica · doi:10.3788/aos240802 · Cited by 2
Li, G., Sheng, L., Duan, B., Li, Y., Song, Y., Zhu, Z., Yan, W. P., Hei, D., & Xing, Q. (2025) · Matter and Radiation at Extremes · doi:10.1063/5.0236541 · Cited by 2
Plug-and-Play Prior for Sparse Hyperspectral Image Unmixing
Yan, W., & Huang, J. (2024) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip64812.2024.10873727 · Cited by 2
Generalized Quantum State Tomography With Hybrid Denoising Priors
Xue, D., Dai, W., Zheng, Z., Li, C., Zou, J., & Xiong, H. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3546655 · Cited by 5
“The pi-oneering work is plug-and-play priors (PnP) [21], [54] inspired by the equivalence between proximal mapping prox λg ( · ) and denoiser D ( · , σ ) : where σ indicates denoising strength, g is an implicit regularization function, and λ is a positive parameter controlling the strength of…”
Controlled learning of pointwise nonlinearities in neural-network-like architectures
Unser, M. A., Goujon, A., & Ducotterd, S. (2025) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2025.101764 · Cited by 2
“These conditions turn out to be crucial for the robustness and convergence of iterative algorithms, either of the proximal gradient type (ISTA, FISTA) [12, 38, 39, 40], or of the plug-and-play type (which requires the non-expansiveness of the denoising step) [41, 42, 43, 44].”
Convergence Analysis of a Proximal Stochastic Denoising Regularization Algorithm
Renaud, M., Hermant, J., & Papadakis, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92369-2_2 · Cited by 2
DeepFRI: A Deep Plug-and-Play Technique for Finite-Rate-of-Innovation Signal Reconstruction
Kamath, A. J., Patil, S. B., & Seelamantula, C. S. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3589394 · Cited by 2
Deep Unfolding-Based Image Reconstruction For Quanta Image Sensors
Otobe, W., Kurihara, K., Maeda, Y., & Hamamoto, T. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084297 · Cited by 2
DIP-based anisotropic total variation regularization for image denoising
Pang, Z., ShangGuan, Y., Jiang, F., & Tai, X. (2025) · Advances in Continuous and Discrete Models · doi:10.1186/s13662-025-03984-y · Cited by 2
An Electromagnetic Inversion Scheme Regularized by Deep Plug-and-Play Denoiser
Gao, L., & Bağcı, H. (2025) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2025.3614886 · Cited by 2
“Recently, a novel method called plug-and-play (PNP) regularization has been introduced in the field of image processing [39].”
Multilevel Plug-and-Play Image Restoration
Laurent, N., Tachella, J. A., Riccietti, E., & Pustelnik, N. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3640427 · Cited by 2
Pereira, A., Rawlik, M., Spindler, S., Kaser, S., Etter, D., Iori, G., Stauber, M., Romano, L., & Stampanoni, M. (2025) · Medical Physics · doi:10.1002/mp.70069 · Cited by 2
Using Randomized Nyström Preconditioners to Accelerate Variational Image Reconstruction
Hong, T., Xu, Z., Hu, J., & Fessler, J. A. (2025) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2025.3622903 · Cited by 2
“Alternatively, one can use plug-and-play (PnP) [9], [10], [11] or regularization by denoising (RED) [12], [13] where one trains a deep denoiser [14] first and then uses it as an implicit prior for general inverse problems.”
RSR-NF: Neural Field Regularization by Static Restoration Priors for Computed Dynamic Imaging
Iskender, B., Bresler, Y., Nakarmi, S., Daphalapurkar, N., & Klasky, M. (2025) · Machine learning for signal processing ... · doi:10.1109/mlsp62443.2025.11204251 · Cited by 2
Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
Pritchard, H., & Parhi, R. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3707068 · Cited by 2
“The plug-and-play (PnP) framework [58] extends PGD by replacing the proximal step prox γg with a generic denoiser D σ .”
PG-DPIR: An Efficient Plug-and-Play Method for High-Count Poisson-Gaussian Inverse Problems
Biquard, M., Chabert, M., Genin, F., Latry, C., & Oberlin, T. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226422 · Cited by 2
Score-Based Turbo Message Passing for Plug-and-Play Compressive Imaging
Cai, C., Jiang, H., Yuan, X., & Zhang, Y. A. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3720360 · Cited by 2
“Building on the denoising interpretation of alternating direction method of multipliers (ADMM), the PnP framework replaces explicit proximal operators with powerful image denoisers, leading to PnP-ADMM [34] and numerous related variants.”
Solving Diffusion Inverse Problems with Restart Posterior Sampling
Ahmed, B., & Makin, J. G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_5 · Cited by 3
Zhang, Y., Zhang, P., Cai, Z., Yu, K., Wang, F., You, H., & Tang, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3647478 · Cited by 2
“Following the plug-and-play paradigm [46], [47], we realize this proximal mapping with the frozen enhancement network F θ (denoted DeepReg ), yielding The input Z k plays the role of a noisy/intermediate estimate, on which the learned proximal operator refines N toward the deep prior while remaining…”
Radio Map Estimation via Latent Domain Plug-and-Play Denoising
Xu, L., Cheng, L., Chen, J., Pu, W., & Fu, X. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3650699 · Cited by 2
“Based on this observation, it is well-motivated to replace the step in (7b) by the following [15], [16]: where D σ denotes the denoiser operating at the noise level with a σ 2 variance.”
InfluentialSPCANet: spatial, pixel and channel attention guided deep image denoiser
Saha, A., Das, D., & Maji, S. K. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21385-5 · Cited by 2
“However, due to the intri-cacies of scenes and the loss of information, image denoising remains a formidable inverse problem [ 3, 4 ] and [ 5 ].”
An Adaptive Multiparameter Penalty Selection Method for Multiconstraint and Multiblock ADMM
Lozenski, L., McCann, M. T., & Wohlberg, B. E. (2026) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2026.3664275 · Cited by 4
“These multiblock optimization problems naturally emerge in several computational imaging applications, such as cases with multiple regularization and data fidelity terms [13], [14] or applying separation of variables for proximal based optimization [15], [16].”
Self-citationTang, C., Dabbech, A., Jackson, A. M., & Wiaux, Y. (2026) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/ae3149 · Cited by 2
All-optical and active compressed ultrafast photography (AA-CUP)
Lu, Y., Meng, Y., Zhang, P., Yin, J., & Chen, F. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115124 · Cited by 2
PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior
Guo, W., Yu, J., Wang, Y., Kang, J. U., & Sun, Y. (2025) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf67917.2025.11443921 · Cited by 6
“Plug-and-play (PnP) methods, for example, alternate between a data-consistency step and a prior step, where advanced denoisers are used as implicit priors [5]–[8].”
Valtchanov, H., Liu, W., Singh, S., Paccoud, J., Alsheghri, A., Dompierre, J., Desrosiers, C., Piché, N., Braïlovski, V., & Guibault, F. (2026) · NDT & E International · doi:10.1016/j.ndteint.2026.103791 · Cited by 2
Hauptmann, A., & Öktem, O. (2026) · Handbook of numerical analysis · doi:10.1016/bs.hna.2026.05.002 · Cited by 2
Multi-dimensional spatial-temporal projection ultrafast compressed imaging
Meng, Y., Zhang, P., Yin, J., Lu, Y., Yue, K., Yin, F., Yang, Q., & Chen, F. (2026) · Light Science & Applications · doi:10.1038/s41377-026-02317-2 · Cited by 2
“Currently, plug-and-play (PnP) algorithms 63 have been widely used to embed deep learning pre-trained denoising networks into the regularization terms of traditional optimization models.”
Channel Estimation in MIMO Systems Using Flow Matching Models
Zhang, Y., & Nadeem, Q.-U.-A. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587599 · Cited by 2
“In this context, the PnP paradigm offers a transformative way to address the regularization subproblem [12].”
Iterative CT image reconstruction using neural network optimization algorithms
Zuo, H., & Zhang, J. (2019) · SPIE Medical Imaging: Physics of Medical Imaging · doi:10.1117/12.2512329 · Cited by 2
“As implemented in the “plug-and-play” algorithm of [11], each iteration of an iterative image reconstruction process is divided into three steps.”
Plug-and-Play Priors for Reconstruction-Based Placental Image Registration
Xing, J., Kamilov, U. S., Wu, W., Wang, Y., & Zhang, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32875-7_15 · Cited by 2
Recent Advancements in Medical Imaging: A Machine Learning Approach
Dang, N., Tiwari, S., Khurana, M., & Arya, K. V. (2021) · Studies in big data · doi:10.1007/978-981-15-9492-2_10 · Cited by 2
Fast Bayesian Model Selection in Imaging Inverse Problems Using Residuals
Vidal, A. F., Pereyra, M., Durmus, A., & Giovannelli, J. (2021) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp49050.2021.9513766 · Cited by 3
“One could also consider more complex priors, such as plug-and-play priors defined via denoising algorithms [8], but then the theoretical guarantees that we establish in Section 3 might not hold.”
Florez-Ospina, J. F., Lau, D. L., Guillot, D., Barner, K. E., & Arce, G. R. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108707 · Cited by 2
Zhu, Q., Liu, B., Cui, Z., Cheng, J., Cao, C., Liu, Y., Liang, D., & Zhu, Y. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac9662 · Cited by 2
Multi-Pose Fusion for Sparse-View CT Reconstruction Using Consensus Equilibrium
Yang, D., Kemp, C. A. J., Buzzard, G. T., & Bouman, C. A. (2022) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton49937.2022.9929347 · Cited by 2
“In particular, MBIR and the more general Plug-and-Play (PnP) methods [13], [14] have been shown to be superior to more traditional direct reconstruction methods such as FDK when the view sampling is very sparse [15].”
Self-citationXu, J. W., & Fu, Z. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103723 · Cited by 2
Phaseless Passive Synthetic Aperture Imaging with Regularized Wirtinger Flow
Aditi, K., Kumar, A. A., Majumdar, A., Chakravarty, T., & Kumar, K. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909573 · Cited by 2
“The ADMM approach helps in application of various denoisers in a Plug-and-play (PnP) manner [15].”
Robust image compression‐encryption via scrambled block bernoulli sampling with diffusion noise
Chen, Z., Ma, C., Wang, T., Feng, Y., Hou, X., & Qian, X. (2022) · IET Image Processing · doi:10.1049/ipr2.12731 · Cited by 2
Tanaka, T., Yatabe, K., & Oikawa, Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095928 · Cited by 2
Dutta, S., Tuador, N. K., Michetti, J., Georgeot, B., Pham, D.-H., Kouamé, D., & Basarab, A. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10289892 · Cited by 5
“A breakthrough was made in the literature in the last decade, enabling the use of a state-of-the-art denoisers instead of an explicit regularization function by redefining the image restoration problem into a chain of denoising processes using the PnP framework [27], [28].”
Hong, T., Pham, T.-A., Yavneh, I., & Unser, M. A. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m1789305 · Cited by 2
“In particular, Beck and Teboulle proposed an accelerated proximal method (APM) [15] by using a dual approach [12].”
Marelli, F., & Liebling, M. (2023) · Optics Express · doi:10.1364/oe.493611 · Cited by 2
“Recently, in the field of 2D image reconstruction, the introduction of Plug-and-Play (PnP) methods has allowed replacing explicit regularization priors with denoising algorithms for image reconstruction [13,14].”
Self-Supervised Hyperspectral Inpainting with the Optimisation inspired Deep Neural Network Prior
Li, S., & Yaghoobi, M. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10289906 · Cited by 2
“In our algorithm, we adopt the PnP-ISTA [15], which has shown promising results over conventional ISTA [16].”
Prior for Multi-Task Inverse Problems in Image Reconstruction Using Deep Equilibrium Models
Willingham, S., Sjöström, M., & Guillemot, C. M. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10289950 · Cited by 4
“A proximal operator is defined as In the Gaussian case, this proximal operator for regularization solves a Gaussian denoising problem, so [3] explains that the proximal operator can be replaced with a denoiser, because the proximal operator does not have to be exact and it is sufficient for it to…”
Fusing Sparsity with Deep Learning for Rotating Scatter Mask Gamma Imaging
Zhu, Y., Scott, C. D., Holland, D. E., Landon, G. V., Fjeldsted, A. P., & Lintereur, A. T. (2022) · IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) · doi:10.1109/nss/mic44845.2022.10399334 · Cited by 2
“Building upon this, Venkatakrishnan et al. [11] proposed the Plug-and-Play (PnP) ADMM framework by plugging advanced image denoising methods into H � ( ) , which do not necessarily correspond to an analytical image prior.”
Iteratively Preconditioned Guidance of Denoising (Diffusion) Models For Image Restoration
Tirer, T. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446692 · Cited by 2
Coded Aperture Snapshot Spectral Imager
Yuan, X., Wu, Z., & Luo, T. (2023) · Springer eBooks · doi:10.1007/978-3-031-39062-3_29 · Cited by 2
Robust Image Restoration with an Adaptive Huber Function Based Fidelity
Song, L., & Huang, H. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02163-y · Cited by 2
Langevin Sampling Plug-and-Play Synthetic Aperture Radar Imaging Algorithm
Wang, Z.-Q., Song, C., Wang, B.-N., Qiu, X.-L., & Xiang, M.-S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3457819 · Cited by 3
“One statistical imaging method is the plug-and-play (PnP) algorithm [7], which substitutes the proximal operator of the prior term with the maximum a posteriori (MAP) denoising step [8].”
InfluentialA Scalable Training Strategy for Blind Multi-Distribution Noise Removal
Zhang, K., Kulshrestha, S., & Metzler, C. A. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3482185 · Cited by 2
Equivariant Denoisers for Image Restoration
Renaud, M., Leclaire, A., & Papadakis, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92366-1_18 · Cited by 2
You KAN do it in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
Cheng, Y., Schönlieb, C., & Avilés-Rivero, A. I. (2026) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-026-01351-4 · Cited by 2
“In general, H σ need not coincide with the proximal operator of any explicit regularisation functional.”
Learning Disentangled Representation for Multidimensional MR Image Reconstruction
Zhao, R., Wang, Z., & Lam, F. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782954 · Cited by 2
“The second popular approach is based on the plug-and-play concept [3], [4].”
Zhong, S., Zhao, X., Liu, D., Su, H., Xie, Z., & Fan, B. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3542150 · Cited by 4
Katsuma, A., Kyochi, S., Ono, S., & Selesnick, I. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3596248 · Cited by 2
“…approach adopted in this study, other examples of non-convex regularizers include meth-ods that integrate deep neural network (DNN)-based models, which have seen remarkable advancements in recent years, into iterative optimization algorithms for signal recovery [38], [39], [40], [41], [42].”
Advancing the Frontiers of Deep Learning for Low-Dose 3D Cone-Beam CT Reconstruction
Biguri, A., Mukherjee, S., Zhao, X., Liu, X., Wang, X., Yang, R., Du, Y., Peng, Y., Brudfors, M., Graham, M. S., et al. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3593189 · Cited by 5
Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
Meanti, G., Ryckeboer, T., Arbel, M., & Mairal, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02634 · Cited by 6
“Recent approaches [12, 23, 44] incorporate diffusion models as priors for the blur kernel, jointly estimating A and x via plug-and-play algorithms [47].”
Arndt, C., & Nickel, J. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/24m1696524 · Cited by 2
Hong, T., Villa, U., & Fessler, J. A. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3655489 · Cited by 2
“An alternative to classical DL pipelines is the Plug-and-Play (PnP) [22] and REgularization-by-Denoising (RED) [23] frameworks.”
Tkaczyk, J. E., Haneda, E., Palma, G., Iordache, R., Klausz, R., Garayt, M., & Carton, A.-K. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2042922 · Cited by 2
Sharpening Hyperspectral Images Using Spatial and Spectral Priors in a Plug-and-Play Algorithm
Teodoro, A. M., Bioucas‐Dias, J. M., & Figueiredo, M. A. T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-78199-0_24 · Cited by 2
Ziabari, A., Rickman, J. M., Drummy, L. F., Simmons, J. P., & Bouman, C. A. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2899499 · Cited by 2
Self-citationA learning based approach to additive, correlated noise removal
Tiirola, J. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.06.003 · Cited by 2
An Iterative Sure-Let Deconvolution Algorithm Based on BM3D Denoiser
Xue, F., Li, J., & Blu, T. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803144 · Cited by 4
“For example, BM3D [9], WNNM [10], and NCSR [11] have been used to replace the proximal operator in IST, FISTA and ADMM for non-linear inverse scattering [12], tomographic reconstruction [13–15], and image superresolution [16].”
Wirtinger Flow Algorithms for Phase Retrieval from Binary Measurements
Kishore, V., & Seelamantula, C. S. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053346 · Cited by 2
Deep Priors Inside an Unrolled and Adaptive Deconvolution Model
Ko, H., Chang, J.-Y., & Ding, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_23 · Cited by 2
“These methods named as plug-and-play frameworks [30, 31] have exploited the concepts from variable splitting techniques like ADMM and HQS, and demonstrated a flexibility on handling various restoration tasks.”
Yogev-Ofer, E., Tirer, T., & Giryes, R. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506499 · Cited by 2
“Follow-up papers of [5] include [6–12], and many more.”
Solving inverse problems with autoencoders on learnt graphs
Majumdar, A. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108300 · Cited by 2
Graph Spectral Image Restoration
Pang, J., & Zeng, J. (2021) · Wiley eBooks · doi:10.1002/9781119850830.ch6 · Cited by 2
Compressed Image Restoration by Combining Trained Dictionary with Plug and Play Framework
Sujithra, M., & Sugitha, N. (2022) · Wireless Personal Communications · doi:10.1007/s11277-022-09490-8 · Cited by 2
“The Gradient projection method [55], Interior point method [56] and Alternating direction method [57]-[58] are the various regularization used for solving the inverse-problem effectively.”
Recent advances of deep learning for spectral snapshot compressive imaging
Suo, J., Wu, Z., Li, Z., & Yuan, X. (2023) · Optoelectronic Imaging and Multimedia Technology · doi:10.1117/12.2641748 · Cited by 2
MCNeT: Measurement-Consistent Networks Via A Deep Implicit Layer For Solving Inverse Problems
Mourya, R., & Mota, J. F. C. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096229 · Cited by 3
“PnP methods [17] modify model-based iterative algorithms, e.”
Convergence Guarantees of Overparametrized Wide Deep Inverse Prior
Buskulic, N., Quéau, Y., & Fadili, J. M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31975-4_31 · Cited by 2
Volumetric Filtering for Shot Gather Interpolation in Swath Seismic Acquisition
Goyes-Peñafiel, P., Vargas, E., Mäkinen, Y., Foi, A., & Argüello, H. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3293486 · Cited by 2
Plug-and-Play Reconstruction with 3D Deep Prior for Complex-Valued Near-Field MIMO Imaging
Oral, O., & Öktem, F. S. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10290090 · Cited by 2
“Despite the recent success of these methods, most of the approaches are developed for 2D and real-valued image reconstruction problems [16]–[18].”
Hybrid Light Field Image Denoising Network using 4D-DCT Separated Transform
Duong, V. V., Huu, T. N., Yim, J., & Jeon, B. (2023) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip59821.2023.10402729 · Cited by 2
“…% ’ ( Since it is an ill-posed inverse problem, we add a regularization term )(cid:2)∙(cid:8) to limit the solution space of x , as follows [22]-[23]: x(cid:28) (cid:23),(cid:24) (cid:20) argmin # $%(cid:7) (cid:23),(cid:24) & (cid:18) (cid:23),(cid:24) x (cid:23),(cid:24) % ’ ( +),x…”
Denoiser-Based Projections for 2D Super-Resolution MRA
Shani, J., Tirer, T., Giryes, R., & Bendory, T. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3394369 · Cited by 3
Henshaw, J., Gibali, A., & Humphries, T. (2025) · Applied Numerical Mathematics · doi:10.1016/j.apnum.2025.10.002 · Cited by 2
Regularized Compression of MRI Data: Modular Optimization of Joint Reconstruction and CodingPreprint
Corona, V., Dar, Y., Williams, G., & Schönlieb, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04065 · Cited by 2
“This recent branch of research attracts great interest, as reflected in a long line of studies presenting new modular algorithms for restoration [14]–[19] and compression [10]– [13] tasks.”
Carruthers Data Processing Pipeline: Photon Background RemovalPreprint
Zhang, A. M., Filippini, H., Craig, J., Waldrop, L., Clarke, J. T., Kamalabadi, F., & Joshi, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.24030 · Cited by 2
“The deblurring algorithm uses a variation of the plug-and-play framework described in Venkatakr-ishnan et al. [19].”
Distributed Radar Autofocus Imaging Using Deep Priors
Mansour, H., Lohit, S., & Boufounos, P. T. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897332 · Cited by 1
Mathematics of biomedical imaging today—a perspective
Betcke, M. M., & Schönlieb, C. (2023) · Progress in Biomedical Engineering · doi:10.1088/2516-1091/acd973 · Cited by 1
“Others are, for example, learned post-processing [59], learned unrolling (or learned iterative schemes) [3, 55, 52] or plug-and-play regularisation [95, 85], see also [8] for a recent review article on the topic.”
Convergence of Nonconvex PNP-ADMM with MMSE Denoisers
Park, C. Y., Shoushtari, S., Gan, W., & Kamilov, U. S. (2023) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap58249.2023.10403463 · Cited by 4
“When h ( x ) = − log ( p x ( x )) , the proximal operator can be interpreted as a maximum a posteriori (MAP) estimator for the additive white Gaussian noise (AWGN) denoising problem The statistical interpretation of the proximal operator as a de-noiser has led to the development of the…”
Wei, D., Li, F. L. F., Shen, X., & Zeng, T. (2024) · CSIAM Transactions on Applied Mathematics · doi:10.4208/csiam-am.so-2023-0037 · Cited by 1
Bayesian Formulation of Regularization by Denoising – Model and Monte Carlo Sampling
Faye, E. C., Fall, M. D., Chetouani, A., & Nicolas Dobigeon, B. (2024) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp61759.2024.10743289 · Cited by 1
Diffusion regularization for multi-parameter near-surface elastic full-waveform inversion
Taufik, M. H., Wang, F., & Alkhalifah, T. A. (2024) · Second International Meeting for Applied Geoscience & Energy · doi:10.1190/image2024-4092707.1 · Cited by 1
Neural network-based inversion of NMR dispersion profiles for enhanced analysis of food systems
Spinelli, G. V., Evangelista, D., Hu, L., & Zama, F. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10859-y · Cited by 1
Noise variances and regularization learning gradient descent network for image deconvolution
Kong, S., Wang, W., Han, Y., & Feng, X. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104391 · Cited by 1
Wang, L., CHENG, L., SHEN, J., & Gu, Y. (2025) · Journal of Mechanics in Medicine and Biology · doi:10.1142/s0219519425400044 · Cited by 1
Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method
Bai, W., Tang, W., Ye, E., Chen, S., Chen, W., & Sun, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889371 · Cited by 1
Kim, T. H. (2025) · IEEE Access · doi:10.1109/access.2025.3552853 · Cited by 1
“Techniques such as physics-based networks [14], [15], Plug-and-Play (PnP) methods [13], [16], [17], [18], and network unrolling [11], [12], [19], [20], [21] combine data-driven priors with MR physics models to further improve reconstruction performance while reducing the reliance on extensive…”
TomoSelfDEQ: Self-supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction
Bubba, T. A., Santacesaria, M., & Sebastiani, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92366-1_26 · Cited by 1
Multi-domain information fusion diffusion model (MDIF-DM) for limited-angle computed tomography
Ma, G., Xia, D., & Zhao, S. (2025) · Journal of X-Ray Science and Technology · doi:10.1177/08953996251339368 · Cited by 1
Plug-and-Play Posterior Sampling for Blind Inverse Problems
Li, A., Gan, W., & Kamilov, U. S. (2025) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp64130.2025.11073296 · Cited by 1
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.