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 901–1,000 of 1,000
Synthetic-data-driven Plug-and-Play method for inverse problems on bivariate signals
Palud, P., Chassande-Mottin, E., & Pılavci, Y. Y. (2025) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp64130.2025.11073317 · Cited by 1
Aerial image quality enhancement via correction of spatially variant aberrations
Du, C., Xiu, J., & Sun, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-19568-5 · Cited by 1
“The PnP method was originally introduced by Venkatakrishnan et al. 37 .”
Maximum a Posteriori Training of Diffusion Models for Image Restoration
Willingham, S., Sjöström, M., & Guillemot, C. M. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226569 · Cited by 2
A multi-constraint based velocity field reconstruction approach for CUP-VISAR
Gan, H., Wang, F., Huang, Y., Li, Y., Guan, Z., & Li, H. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115627 · Cited by 1
Integrating Model-Based Reconstruction and Deep Learning for Accelerating Mass Spectrometry Imaging
Anandakumar, M., Trinklein, T. J., Rubakhin, S. S., Sweedler, J. V., & Lam, F. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.5c04075 · Cited by 1
Restora-Flow: Mask-Guided Image Restoration with Flow Matching
Hadzic, A., Thaler, F., Bogensperger, L., Joham, S. J., & Urschler, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00480 · Cited by 1
“Instead, PnP-Flow [25] combines Plug-and-Play methods [33] with flow matching without requiring backpropagation, however, it tends to produce over-smoothed results.”
Enhancing convolutional neural network generalizability via low‐rank weight approximation
Gao, C., Yang, S., & Zhang, A. R. (2025) · IET Image Processing · doi:10.1049/ipr2.13205 · Cited by 1
Split, Skip and Play: Variance-Reduced Proxskip for Tomography Reconstruction is Extremely Fast
Papoutsellis, E., Kereta, Ž., & Papafitsoros, K. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630564 · Cited by 1
“Alternatively, one can use learned implicit priors, e.g. plug-and-play (PnP) approaches [2], where classical proximal regularisation is replaced by a denoiser, such as BM3D [3] or a pretrained neural network.”
Fast Electrical Impedance Tomography With Hybrid Priors
Shi, S., Kang, R., & Liatsis, P. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3664753 · Cited by 1
“Plug-and-play alternating direction method of multipliers (PnP-ADMM) [13] represents an innovative framework that harmoniously integrates classical optimization techniques with deep learning approaches.”
U-PnP-ADMM: Uncertainty-Aware Plug-and-Play ADMM for Robust Night Vision Enhancement
Baraha, S., & Sahoo, A. K. (2025) · IEEE India Conference · doi:10.1109/indicon68490.2025.11393045 · Cited by 1
“In parallel, generic opti-2025 mization frameworks such as Plug-and-Play ADMM [11] and Regularization by Denoising (RED) [12] have demonstrated the ability to integrate advanced denoisers as priors, offering flexibility and theoretical convergence guarantees.”
sFWI: physics-informed score-based generative modeling for robust full waveform inversion
Gai, Z., & Wang, Y. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae55fb · Cited by 1
A plug-and-play approach with fast uncertainty quantification for weak-lensing mass mapping
Leterme, H., Tersenov, A., Fadili, J. M., & Starck, J. (2026) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202557652 · Cited by 5
Suzuki, Y., & Ono, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465057 · Cited by 1
Brault, D., Riedel, F., Fournier, C., Olivier, T., & Denis, L. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3694142 · Cited by 1
“Nevertheless,theyarecomputationallyexpensiveand dependeitheronclosed-formregularizationpriors,oronlearned regularizationpriors[23],[24],[25]whichrequiregroundtruth data for training.”
Atashyan, A., Hayrapetyan, D., Poghosyan, V., Poghosyan, S., Egiazarian, K., & Shoukourian, Y. H. (2026) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661825701305 · Cited by 1
“These denoisers also fit naturally into modern reconstruction frameworks like plug-and-play priors [15] and can be combined with learned modules for additional gains.”
Alternating Subspace Method for Sparse Recovery of Signals
Zhu, X., Ma, Y., Li, X., & Li, T. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3695936 · Cited by 1
“This flex-ibility is inherited from the plug-and-play (PnP) framework prevalent in ADMM-like methods [11], [12], [13], where de-noisers can be substituted in a plug-and-play manner or even modeled as learnable neural networks [14], [15].”
Physics-Aware Deep Learning for SAR and InSAR Remote Sensing: Models, Methods, and Open Challenges
Taricco, G. (2026) · Remote Sensing · doi:10.3390/rs18152567 · Cited by 2
Bayesian Signal Component Decomposition via Diffusion-Within-Gibbs Sampling
Zhang, Y., Guo, R., & Eldar, Y. C. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3721152 · Cited by 1
“In optimization-based approaches, plug-and-play methods [18], [19] replace the proximal operators of explicit regularizers in certain proximal-type algorithms (e.g., ADMM [20]) by powerful learned denoisers, while preserving modular treatment of the sensing operators; yet existing theory usually…”
Xiao, S., Zeng, Y., Rong, H., & Tang, Y. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3739531 · Cited by 1
“It then performs posterior inference to obtain the constructed CKM by combining the shared prior p ( x ) with the local likelihood p ( y | x ) in a plug-and-play manner [24], [25], so that changing tasks or device front ends affects A ( · ) and the likelihood term, rather than the shared prior.”
Convex Analysis and Convex Optimization
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.033 · Cited by 1
Sparsity Based Nonlocal Image Restoration: An Alternating Optimization Approach
Li, X., Dong, W., & Shi, G. (2017) · Springer eBooks · doi:10.1007/978-3-319-61609-4_7 · Cited by 1
Physics based modeling for the development of soft segmentation and reconstruction algorithms
Ziabari, A., Rickman, J. M., Simmons, J. P., & Bouman, C. A. (2017) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2017.8335688 · Cited by 1
Self-citationPlug-and-Play Based Optimization Algorithm for New Crime Density Estimation
Feng, X., Zhao, C., Peng, S., Hu, X., & Ouyang, Z.-W. (2019) · Journal of Computer Science and Technology · doi:10.1007/s11390-019-1920-1 · Cited by 1
Kazantsev, D., Pasca, E., Basham, M., Turner, M. J. L., Ehrhardt, M. J., Thielemans, K., Thomas, B. A., Ovtchinnikov, E., Withers, P. J., & Ashton, A. (2019) · International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine (Fully3D) · doi:10.1117/12.2534289 · Cited by 1
Image Inpainting by Low-Rank Prior and Iterative Denoising
Han, R., Wang, S.-M., Fu, S., Li, Y., Liu, S., & Zhou, W.-F. (2020) · IEEE Access · doi:10.1109/access.2020.3007204 · Cited by 1
“Inspired by Plug-and-Play framework [28], Tom and Raja proposed iterative denoising and backward projections(IDBP-BM3D) [29] algorithm, they used an image denoising method to solve the image inpainting problem.”
Lp-Method-Noise Based Regularization Model for Image Restoration
Wang, Y., Zhao, C., Jiao, H., & Wang, X. (2020) · IEEE Access · doi:10.1109/access.2020.3015140 · Cited by 1
Video Image Deblurring Algorithm Based on Denoising Engine
Li, M., Sun, D., Lu, Y., Gao, Q., & Liu, Y. (2021) · International Conference on Information Communication and Software Engineering (ICICSE) · doi:10.1109/icicse52190.2021.9404106 · Cited by 1
“In [4], [5], a plug and play algorithm is proposed, which decomposes the inverse problem of image restoration into a series of image denoising tasks and iterates through the successive application of image denoising.”
Calibrationless MRI Reconstruction With A Plug-In Denoiser
Zhao, S., Potter, L. C., & Ahmad, R. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9433815 · Cited by 1
Dar, Y., & Bruckstein, A. M. (2021) · Springer eBooks · doi:10.1007/978-3-030-03009-4_71-1 · Cited by 1
“…(ADMM) (Boyd et al. 2011) was used to form iterative structures based on denoising modules to solve inverse imaging problems (specifically, demonstrated by Venkatakrishnan et al. (2013) and Sreehari et al. (2016) for tomographic reconstruction based on the BM3D denoiser (Dabov et al. 2007)).”
From Compressed Sensing to Deep Learning
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.023 · Cited by 1
Compressed Sensing for Imaging
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.019 · Cited by 1
Zhu, Q., & Liang, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87589-3_46 · Cited by 1
Consensus Equilibrium for Subsurface Delineation
Yang, H. J., Lin, Y., Wohlberg, B. E., & Tartakovsky, D. M. (2021) · Water Resources Research · doi:10.1029/2021wr030151 · Cited by 1
“ The main advantage of the CE framework over optimization-based methods is that other non-expansive operators, called agents, can be employed in lieu of the proximal mapping operator i E F (Bouman, 2013; Buzzard et al., 2018).”
Self-citationAdcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.009 · Cited by 2
KERNEL-BASED IMAGE FILTERING: FAST ALGORITHMS AND APPLICATIONS
Ghosh, S. (2019) · doi:10.1145/3366344.3366444 · Cited by 1
van Gogh, S., Mukherjee, S., Rawlik, M., Wang, Z., Xu, J., Varga, Z., Schönlieb, C., & Stampanoni, M. (2022) · International Conference on Image Formation in X-Ray Computed Tomography (CT Meeting) · doi:10.1117/12.2646437 · Cited by 1
Quantitative susceptibility mapping using plug-and-play alternating direction method of multipliers
Iyer, S. K., Moon, B. F., Josselyn, N. J., Kurtz, R. M., Song, J. W., Ware, J. B., Nabavizadeh, S. A., & Witschey, W. R. T. (2022) · Scientific Reports · doi:10.1038/s41598-022-22778-w · Cited by 3
“The proposed reconstruction formulation performs better than existing popular QSM approaches when compared using global quality metrics such as HFEN, SSIM, CC and MI, and also achieves sharper edges and better retention of fine features in the reconstructed images.”
Li, B., Ma, C., Ersoy, O. K., Pan, Z., Wen, W., Sun, Z., & Gao, W. (2022) · IEEE photonics journal · doi:10.1109/jphot.2022.3230422 · Cited by 1
Sparse Regularized CT Reconstruction: An Optimization Perspective
Morotti, E., & Piccolomini, E. L. (2023) · Springer eBooks · doi:10.1007/978-3-030-98661-2_123 · Cited by 1
Volume Conservation Constrained Multi-Material Reconstruction for Inconsistent Spectral CT Imaging
Yu, X., Cai, A., Liang, N., Wang, S., Li, L., & Yan, B. (2023) · IEEE Access · doi:10.1109/access.2023.3261661 · Cited by 1
“Rather than the TV penalty, we also consider a deep prior, DnCNN, as a flexible module under the plug-and-play (PnP) framework [35].”
Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval
Agrawal, R., & Leong, O. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096782 · Cited by 1
Li, Q., & Wang, W. (2023) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001423540149 · Cited by 1
Besnard, S., Jurie, F., & Fadili, J. M. (2023) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers61460.2023.10430751 · Cited by 1
Ge, T., Liao, R., Medrano, M., Politte, D. G., Williamson, J. F., & O’Sullivan, J. A. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad00fb · Cited by 1
Shi, H., Traonmilin, Y., & Aujol, J. (2024) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-024-01178-x · Cited by 1
Wang, C., & Li, J. (2023) · Applied Mathematics for Modern Challenges · doi:10.3934/ammc.2023012 · Cited by 1
Rastogi, A., & Yalavarthy, P. K. (2024) · Medical Physics · doi:10.1002/mp.16935 · Cited by 1
Empirical Bayesian Imaging With Large-Scale Push-Forward Generative Priors
Melidonis, S., Holden, M., Altmann, Y., Pereyra, M., & Zygalakis, K. C. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3361806 · Cited by 4
“Such priors are often data-driven and use machine learning techniques to encode prior knowledge available in the form of a training dataset (see, e.g., [7], [8], [9], [10], [11], [12], [13], [14], [15]).”
Image Restoration with Generalized L2 Loss and Convergent Plug-and-Play Priors
Nareddy, K. K. R., Kamath, A. J., & Seelamantula, C. S. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446244 · Cited by 1
“Venkatkrishnan et al. [14] interpreted the proximal operation as equivalent to denoising, and introduced the plug-and-play (PnP) framework [15], which allows one to incorporate a more powerful denoiser D θ : R n → R n instead of the proximal operator, where θ denotes the parameters of the denoiser.”
Variational Analysis of Adversarial Regularization for Solving Inverse Problems
Bhandiwad, A. S., Kamath, A. J., Asokan, S., & Seelamantula, C. S. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446385 · Cited by 1
Method of Alternating Proximations for Solving Linear Inverse Problems
Kamath, A. J., Reddy, N. K. K., & Seelamantula, C. S. (2024) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom60851.2024.10631653 · Cited by 1
Iterative Operator Sketching Framework for Large-Scale Imaging Inverse Problems
Tang, J., Mukherjee, S., & Schönlieb, C. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890355 · Cited by 1
Xiao, M., Wang, Z., Guo, J., Guo, D., & Qu, X. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647882 · Cited by 1
Mobile Aware Denoiser Network (MADNet) for Quad Bayer Images
Madhusudana, P. C., Li, J., Nadir, Z., Sheikh, H. R., & Lee, S.-J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00009 · Cited by 1
Electromagnetic Inversion Regularized by a Plug-and-Play Deep Neural Network Denoiser
Gao, L., & Bağcı, H. (2024) · Digest - IEEE Antennas and Propagation Society. International Symposium · doi:10.1109/ap-s/inc-usnc-ursi52054.2024.10686043 · Cited by 1
CT image super-resolution under the guidance of deep gradient information
Shen, Y., Liang, N., Zhong, X., Ren, J., Zheng, Z., Li, L., & Yan, B. (2024) · Journal of X-Ray Science and Technology · doi:10.1177/08953996241289225 · Cited by 1
He, T., Jiang, X., Wu, J., Wang, W. X., Zhang, H., & Li, Z. (2024) · IEEE International Conference on Medical Artificial Intelligence (MedAI) · doi:10.1109/medai62885.2024.00043 · Cited by 1
Extending InSAR2InSAR to Sentinel-1 Data
Geara, C., Gelas, C., Vitry, L. D., Colin‐Koeniguer, E., & Florence Tupin, D. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3558363 · Cited by 1
Pre-capture Privacy via Adaptive Single-Pixel Imaging
Sogabe, Y., Sugimoto, S., Matsumoto, A., & Kitahara, M. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00877 · Cited by 1
“In this section, we evaluate three different reconstruction methods: ADMM-CSNet which is not jointly trained, the alternating directions method of multipliers (ADMM) [5] with total variation (TV) [30] regularization, and plug-and-play (PnP) [38] with BM3D [7], as shown in Figure 9.”
Learning to solve inverse problems end-to-end
Heckel, R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780198947172.003.0006 · Cited by 1
Heckel, R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780198947172.003.0008 · Cited by 1
Mixed noise removal via generalized gaussian scale mixture modeling and plug-and-play deep prior
Xu, H., Lu, J., Weng, S., & Li, F. (2025) · Numerical Algorithms · doi:10.1007/s11075-025-02103-y · Cited by 2
External Division of Two Proximity Operators—Part I: Debiased Feature Grouping
Suzuki, K., & Yukawa, M. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3619197 · Cited by 1
External Division of Two Proximity Operators—Part II: Generalization and Properties
Suzuki, K., & Yukawa, M. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3619190 · Cited by 1
“Plug-and-play [21], on the other hand, replaces the proximity operator in the proximal splitting methods by some effective de-noiser, instead of designing R directly.”
Adaptive Multimodal Protein Plug-And-Play With Diffusion-Based Priors
Banerjee, A., Xu, X., Moosmüller, C., & Lee, H. (2025) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap66162.2025.11423984 · Cited by 2
Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers
Unser, M. A., & Ducotterd, S. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m176297x · Cited by 4
“This is exemplified in the plug-and-play (PnP) framework [77, 44], where deep-learning-based denoisers replace traditional proximal operators [19, 70, 74].”
A Machine Learning Based Framework for the Smart Healthcare MonitoringPreprint
Zahin, A., Tan, L. T., & Hu, R. Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03360 · Cited by 1
“ich is ω for our case. We treat it as a tunable knob to control the amount of denoising because the residual, v −˜v(k) at kth iteration is not exactly Gaussian [11]. Thanks to this modular structure, [10] proposed that in the case of ADMM, one does not need to specify g before running the ADMM. Instead, they replace (…”
Single and dual-energy computed tomography guided radiation therapy
Lyu, Q. (2021) · eScholarship (California Digital Library) · Cited by 1
Plug-and-play optimization for pixel super-resolution phase retrievalPreprint
Chang, X., Bian, L., Jiang, S., Zheng, G., & Zhang, J. (2021) · arXiv (Cornell University) · Cited by 1
Interpretation of Plug-and-Play (PnP) algorithms from a different anglePreprint
Nayak, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07795 · Cited by 1
“This motivated, authors in [14], to replace the ProxσR operator in the denoising step of ADMM by an off-the-shelf denoiser Hσ, with denoising strength corresponding to noise level σ, and termed it as the PnP-algorithm (plug-and-play method).”
MoDIR: Motion-Compensated Training for Deep Image Reconstruction without Ground TruthPreprint
Gan, W., Sun, Y., Eldeniz, C., Liu, J., An, H., & Kamilov, U. S. (2021) · arXiv (Cornell University) · Cited by 1
Ge, T., Medrano, M., Liao, R., Politte, D. G., Williamson, J. F., & O’Sullivan, J. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00109 · Cited by 1
Instabilities in Plug-and-Play (PnP) algorithms from a learned denoiserPreprint
Nayak, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01655 · Cited by 1
Stochastic Primal-Dual Deep Unrolling Networks for Imaging Inverse Problems.Preprint
Tang, J. (2021) · arXiv (Cornell University) · Cited by 1
High-Definition from Above : Advancing Satellite Imagery Super-Resolution via Self-Supervision
Nguyen, N.-L. (2023) · theses.fr (ABES) · doi:10.70675/82bf07bcz9681z49bfz9cf6zb60fad9163ee · Cited by 2
Ramzi, Z. (2022) · theses.fr (ABES) · doi:10.70675/17b99897zf4a1z45d6zb759zba72ce6bda41 · Cited by 4
Zero-Shot Solving of Imaging Inverse Problems Via Noise-Refined Likelihood Guided Diffusion ModelsPreprint
Wang, Z., Liu, H., & Wei, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5295204 · Cited by 1
Eleven Primitives and Three Gates: The Universal Structure of Computational ImagingPreprint
Yang, C., & Yuan, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.13521 · Cited by 1
Gasnier, N. (2022) · theses.fr (ABES) · doi:10.70675/e41a1058z7945z416bz8592zac5f8ad6b38c · Cited by 3
Advanced super-resolution techniques for high quality scanned images
Rashidi, A. (2022) · theses.fr (ABES) · doi:10.70675/8e707b29z4eedz4fcdz9ae4z4f430d2db51c · Cited by 1
Hurault, S. (2023) · theses.fr (ABES) · doi:10.70675/e9779322ze5f2z4846z9a94z4360e51b13e4 · Cited by 16
Multiscale Fourier Neural Operator for Inverse Wave Scattering in Highly Oscillatory MediaPreprint
You, Z., Xu, Z., & Cai, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.08448 · Cited by 1
Can one regularizer reproduce posterior means at two noise levels?Preprint
Liu, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.13926 · Cited by 1
“It is also relevant to reconstruction methods that use denoisers in proximal iterations [9] or construct regularization objectives from them [10].”
Simultaneous sparse coding with Laplacian scale mixture prior for image restoration
Lu, X., Lü, X., & Zuo, Y. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.5.053009
Compressive Focal Plane Array Imager Reconstruction Using Learning Based Regularization
Kar, O. F., Güngör, A., & Güven, H. E. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806369
“[8] Singanallur V Venkatakrishnan, Charles A Bouman, and Brendt Wohlberg, “Plug-and-play priors for model based reconstruction,” in Global Conference on Signal and Information Processing (GlobalSIP), 2013 IEEE.”
Robust Single Image Super Resolution Employing ADMM with Plug-and-Play Prior
Rahiman, V. A., & George, S. N. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-32-9291-8_25
Infusing Learned Priors into Model-Based Multispectral ImagingPreprint
Liu, J., Sun, Y., & Kamilov, U. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09313
“This explicit control in the strength of regularization is one of the key differences between RED and an alternative plug-and-play priors (PnP) framework [25–27].”
An embedding framework for video reconstruction using Gaussian mixture models
Ghassab, V. K., & Bouguila, N. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.8969506
“The algorithm that we propose in this section is an extention of the conventional ADMM [4], [5].”
Noise2Inverse: Self-supervised deep convolutional denoising for linear image reconstruction.Preprint
Hendriksen, A. A., Pelt, D. M., & Batenburg, K. J. (2020) · arXiv (Cornell University)
Kernel Regularization for Image Restoration
Unni, V. S., & Chaudhury, K. N. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190938
“Starting with the original paper [10], it was demonstrated in [11, 16, 17, 18], that this so-called plug-and-play (PnP) method can produce promising restoration results using state-of-the-art denoisers.”
InfluentialKatkovnik, V. Y., Shevkunov, I. A., & Egiazarian, K. (2021) · Optical Engineering · doi:10.1117/1.oe.60.1.013108
Sampling Strategies for Compressive Imaging
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.020
An Introduction to Conventional Compressed Sensing
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.008
Techniques for Enhancing Performance
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.006
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.022
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.015
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.034
Compressed Sensing, Optimization and Wavelets
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.007
The Essentials of Compressive Imaging
Adcock, B., & Hansen, A. C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108377447.003
Coded wavefront sensor and non-iterative learning-based reconstruction
Qi, M., Wang, C., & Heidrich, W. (2021) · Imaging and Applied Optics · doi:10.1364/cosi.2021.cf2b.7
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.