{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:15:07Z","timestamp":1792253707082,"version":"4.4.0"},"reference-count":78,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/100008996","name":"Capital Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008996","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People\u2019s Republic of China","doi-asserted-by":"publisher","award":["KF202401"],"award-info":[{"award-number":["KF202401"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>The pretrained diffusion model as a strong prior has been leveraged to address inverse problems in a zero-shot manner without task-specific retraining. Different from the unconditional generation, the measurement-guided generation requires estimating the expectation of a clean image given the current image and the measurement. With the theoretical expectation expression, the crucial task of solving inverse problems is to estimate the noisy likelihood function at the intermediate image sample. Using the Tweedie\u2019s formula and the known noise model, the existing diffusion posterior sampling methods perform a gradient descent step with backpropagation through the pretrained diffusion model. To alleviate the costly computation and intensive memory consumption of the backpropagation, we propose an alternative maximum-a-posteriori-based\u00a0(MAP-based) surrogate estimator to the expectation. With this approach and further density approximation, the MAP estimator for the linear inverse problem is the solution to a traditional regularized optimization, of which the loss comprises a data fidelity term and the diffusion model related prior term. Integrating the MAP estimator into a general denoising diffusion implicit model\u2013like sampler, we achieve the general solving framework for inverse problems. Our approach highly resembles the existing [Formula: see text]GDM without the manifold projection operation of the gradient descent direction. The developed method is also extended to nonlinear JPEG decompression. The performance of the proposed posterior sampling is validated across a series of inverse problems, where both VP and VE SDE-based pretrained diffusion models are taken into consideration.<\/jats:p>","DOI":"10.1137\/24m1688321","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T03:53:07Z","timestamp":1749009187000},"page":"1468-1492","source":"Crossref","is-referenced-by-count":7,"title":["Efficient Diffusion Posterior Sampling for Noisy Inverse Problems"],"prefix":"10.1137","volume":"18","author":[{"given":"Ji","family":"Li","sequence":"first","affiliation":[{"name":"Academy for Multidisciplinary Studies, Capital Normal University, Beijing, 100048 China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University of Kansas Medical Center, Kansas City, KS 66103 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref2","unstructured":"J. Arbas, H. Ashtiani, and C. Liaw, Polynomial time and private learning of unbounded Gaussian mixture models, in Proceedings of the International Conference on Machine Learning, PMLR, 2023, pp. 1018\u20131040."},{"key":"ref3","unstructured":"A. Bora, A. Jalal, E. Price, and A. G. Dimakis, Compressed sensing using generative models, in Proceedings of the International Conference on Machine Learning, PMLR, 2017, pp. 537\u2013546."},{"key":"ref4","unstructured":"B. Boys, M. Girolami, J. Pidstrigach, S. Reich, A. Mosca, and O. D. Akyildiz, Tweedie Moment Projected Diffusions for Inverse Problems, Trans. Mach. Learn. Res. (2024), to appear."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1090\/S0894-0347-2012-00740-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1134\/S1061830916040033"},{"key":"ref7","first-page":"227","volume":"9","author":"Chambolle A.","year":"2010","journal-title":"Theoretical Found. Numer. Methods Sparse Recovery"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28831-7_2"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"J. Choi, S. Kim, Y. Jeong, Y. Gwon, and S. Yoon, ILVR: Conditioning method for denoising diffusion probabilistic models, in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, 2021, pp. 14347\u201314356.","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref10","unstructured":"H. Chung, J. Kim, M. T. Mccann, M. L. Klasky, and J. C. Ye, Diffusion posterior sampling for general noisy inverse problems, in Proceedings of the 11th International Conference on Learning Representations, 2022."},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"H. Chung, B. Sim, D. Ryu, and J. C. Ye, Improving diffusion models for inverse problems using manifold constraints, in Proceedings of the 36th International Conference on Neural Information Processing Systems, 2022, pp. 25683\u201325696.","DOI":"10.52202\/068431-1862"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"H. Chung, B. Sim, and J. C. Ye, Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse problems through stochastic contraction, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12413\u201312422.","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102479"},{"key":"ref14","author":"Delbracio M.","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L. Fei-Fei, Imagenet: A large-scale hierarchical image database, in Proceedings of the Conference on Computer Vision and Pattern Recognition, IEEE, 2009, pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","unstructured":"P. Dhariwal and A. Nichol, Diffusion models beat GANs on image synthesis, in Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021, pp. 8780\u20138794."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab831a"},{"key":"ref18","unstructured":"L. Dinh, J. Sohl-Dickstein, and S. Bengio, Density estimation using real NVP, in International Conference on Learning Representations, 2017."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2011.06.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"B. T. Feng, J. Smith, M. Rubinstein, H. Chang, K. L. Bouman, and W. T. Freeman, Score-based diffusion models as principled priors for inverse imaging, in Proceedings of the International Conference on Computer Vision (ICCV), IEEE, 2023.","DOI":"10.1109\/ICCV51070.2023.00965"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"S. Gao, X. Liu, B. Zeng, S. Xu, Y. Li, X. Luo, J. Liu, X. Zhen, and B. Zhang, Implicit diffusion models for continuous super-resolution, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10021\u201310030.","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"A. Graikos, N. Malkin, N. Jojic, and D. Samaras, Diffusion models as plug-and-play priors, in Proceedings of the 36th International Conference on Neural Information Processing Systems, 2022, pp. 14715\u201314728.","DOI":"10.52202\/068431-1070"},{"key":"ref25","unstructured":"J. Ho, A. Jain, and P. Abbeel, Denoising diffusion probabilistic models, in\u00a0Proceedings of the 34th International Conference on Neural Information Processing Systems 2020, pp. 6840\u20136851."},{"key":"ref26","unstructured":"S. Hurault, A. Leclaire, and N. Papadakis, Gradient step denoiser for convergent plug-and-play, in Proceedings of the International Conference on Learning Representations, 2022, https:\/\/openreview.net\/forum?id=fPhKeld3Okz."},{"key":"ref27","unstructured":"S. Hurault, A. Leclaire, and N. Papadakis, Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization, in Proceedings of the International Conference on Machine Learning, PMLR, 2022, pp. 9483\u20139505."},{"key":"ref28","first-page":"14938","volume":"34","author":"Jalal A.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","first-page":"13242","volume":"34","author":"Kadkhodaie Z.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"T. Karras, M. Aittala, T. Aila, and S. Laine, Elucidating the design space of diffusion-based generative models, in Proceedings of the 36th International Conference on Neural Information Processing Systems, 2022, pp. 26565\u201326577.","DOI":"10.52202\/068431-1926"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"T. Karras, S. Laine, and T. Aila, A style-based generator architecture for generative adversarial networks, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref32","volume-title":"Advances in Neural Information Processing Systems","author":"Kawar B.","year":"2022"},{"key":"ref33","volume-title":"NeurIPS Workshop on Score-Based Methods","author":"Kawar B.","year":"2022"},{"key":"ref34","unstructured":"B. Kawar, G. Vaksman, and M. Elad, SNIPS: Solving noisy inverse problems stochastically, in Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021, pp. 21757\u201321769."},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"B. Kawar, G. Vaksman, and M. Elad, Stochastic image denoising by sampling from the posterior distribution, in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 1866\u20131875.","DOI":"10.1109\/ICCVW54120.2021.00213"},{"key":"ref36","unstructured":"D. P. Kingma and P. Dhariwal, Glow: Generative flow with invertible 1x1 convolutions, in Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018."},{"key":"ref37","unstructured":"D. P. Kingma and M. Welling, Auto-encoding variational Bayes, in International Conference on Learning Representations, 2014."},{"key":"ref38","unstructured":"X. Li, S. M. Kwon, I. R. Alkhouri, S. Ravishanka, and Q. Qu, Decoupled Data Consistency with Diffusion Purification for Image Restoration, preprint, arXiv:2403.06054, 2024."},{"key":"ref39","author":"Liang Z.-P.","year":"2000","journal-title":"SPIE Optical Engineering Press"},{"key":"ref40","unstructured":"G.H. Liu, A. Vahdat, D.A. Huang, E. Theodorou, W. Nie, and A. Anandkumar, I\\(^2\\)SB: Image-to-image Schr\u00f6dinger bridge, in Proceedings of the 40th International Conference on Machine Learning, A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, and J. Scarlett, eds. PMLR, 2023, pp. 22042\u201322062, https:\/\/proceedings.mlr.press\/v202\/liu23ai.html."},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"J. Liu, R. Anirudh, J. J. Thiagarajan, S. He, K. A. Mohan, U. S. Kamilov, and H. Kim, Dolce: A model-based probabilistic diffusion framework for limited-angle CT reconstruction, in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 10498\u201310508.","DOI":"10.1109\/ICCV51070.2023.00963"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"J. Liu, T. Kuang, and X. Zhang, Image reconstruction by splitting deep learning regularization from iterative inversion, in Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2018, pp. 224\u2013231.","DOI":"10.1007\/978-3-030-00928-1_26"},{"key":"ref43","doi-asserted-by":"crossref","unstructured":"A. Lugmayr, M. Danelljan, A. Romero, F. Yu, R. Timofte, and L. Van Gool, RePaint: Inpainting using denoising diffusion probabilistic models, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11461\u201311471.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref44","unstructured":"Z. Luo, F. K. Gustafsson, Z. Zhao, J. Sj\u00f6lund, and T. B. Sch\u00f6n, Image restoration with mean-reverting stochastic differential equations, in Proceedings of the International Conference on Machine Learning, 2023."},{"key":"ref45","unstructured":"S. Martin, A. Gagneux, P. Hagemann, and G. Steidl, PnP-flow: Plug-and-play image restoration with flow matching, in International Conference on Learning Representations, 2024."},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"T. Meinhardt, M. Moller, C. Hazirbas, and D. Cremers, Learning proximal operators: Using denoising networks for regularizing inverse imaging problems, in Proceedings of ICCV, 2017, pp. 1781\u20131790.","DOI":"10.1109\/ICCV.2017.198"},{"key":"ref47","unstructured":"X. Meng and Y. Kabashima, Diffusion model based posterior sampling for noisy linear inverse problems, in Asian Conference on Machine Learning, PMLR, 2025, pp. 623\u2013638."},{"key":"ref48","doi-asserted-by":"crossref","unstructured":"A. Mousavi, A. Patel, and R. Baraniuk, A deep learning approach to structured signal recovery, in Proceedings of Allerton, IEEE, 2015, pp. 1336\u20131343.","DOI":"10.1109\/ALLERTON.2015.7447163"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"Y. Nan, Y. Quan, and H. Ji, Variational-EM-based deep learning for noise-blind image deblurring, in Proceedings of CVPR, 2020, pp. 3626\u20133635.","DOI":"10.1109\/CVPR42600.2020.00368"},{"key":"ref50","unstructured":"B. Ozturkler, M. Mardani, A. Vahdat, J. Kautz, and J. M. Pauly, Regularization by denoising diffusion process for MRI reconstruction, in Proceedings of Medical Imaging with Deep Learning, 2023."},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"X. Pan, X. Zhan, B. Dai, D. Lin, C. C. Loy, and P. Luo, Exploiting deep generative prior for versatile image restoration and manipulation, in Proceedings of Computer Vision\u2013ECCV 2020: 16th European Conference, Part II, 2020, pp. 262\u2013277.","DOI":"10.1007\/978-3-030-58536-5_16"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115428"},{"key":"ref53","unstructured":"X. Peng, Z. Zheng, W. Dai, N. Xiao, C. Li, J. Zou, and H. Xiong, Improving diffusion models for inverse problems using optimal posterior covariance, in Proceedings of the 41st International Conference on Machine Learning, R. Salakhutdinov, Z. Kolter, K. Heller, A. Weller, N. Oliver, J. Scarlett, and F. Berkenkamp, eds. PMLR, 2024, pp. 40347\u201340370."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-019-01470-9"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-014-9893-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref57","unstructured":"E. Ryu, J. Liu, S. Wang, X. Chen, Z. Wang, and W. Yin, Plug-and-play methods provably converge with properly trained denoisers, in Proceedings of the International Conference on Machine Learning, PMLR, 2019, pp. 5546\u20135557."},{"key":"ref58","doi-asserted-by":"crossref","unstructured":"C. Saharia, W. Chan, H. Chang, C. Lee, J. Ho, T. Salimans, D. Fleet, and M. Norouzi, Palette: Image-to-image diffusion models, in Proceedings of ACM, SIGGRAPH 2022, pp. 1\u201310.","DOI":"10.1145\/3528233.3530757"},{"key":"ref59","first-page":"4713","volume":"45","author":"Saharia C.","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref60","doi-asserted-by":"crossref","unstructured":"W. Shi, F. Jiang, S. Liu, and D. Zhao, Scalable convolutional neural network for image compressed sensing, in Proceedings of CVPR, 2019, pp. 12290\u201312299.","DOI":"10.1109\/CVPR.2019.01257"},{"key":"ref61","unstructured":"J. Song, C. Meng, and S. Ermon, Denoising diffusion implicit models, in Proceedings of ICLR, 2021."},{"key":"ref62","unstructured":"J. Song, A. Vahdat, M. Mardani, and J. Kautz, Pseudoinverse-guided diffusion models for inverse problems, in Proceedings of the International Conference on Learning Representations, 2022."},{"key":"ref63","first-page":"1415","volume":"34","author":"Song Y.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64","unstructured":"Y. Song and S. Ermon, Generative modeling by estimating gradients of the data distribution, in Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019, pp. 11918\u201311930."},{"key":"ref65","unstructured":"Y. Song, L. Shen, L. Xing, and S. Ermon, Solving inverse problems in medical imaging with score-based generative models, in Proceedings of the International Conference on Learning Representations, 2021."},{"key":"ref66","unstructured":"Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, and B. Poole, Score-based generative modeling through stochastic differential equations, in Proceedings of the International Conference on Learning Representations, 2020."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2893568"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1137\/23M157185X"},{"key":"ref69","unstructured":"Y. Wang, J. Yu, and J. Zhang, Zero-shot image restoration using denoising diffusion null-space model, in Proceedings of the 11th International Conference on Learning Representations, 2022."},{"key":"ref70","doi-asserted-by":"crossref","unstructured":"J. Whang, M. Delbracio, H. Talebi, C. Saharia, A. G. Dimakis, and P. Milanfar, Deblurring via stochastic refinement, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16293\u201316303.","DOI":"10.1109\/CVPR52688.2022.01581"},{"key":"ref71","unstructured":"J. Whang, Q. Lei, and A. Dimakis, Solving inverse problems with a flow-based noise model, in Proceedings of the International Conference on Machine Learning, PMLR, 2021, pp. 11146\u201311157."},{"key":"ref72","doi-asserted-by":"crossref","unstructured":"B. Xia, Y. Zhang, S. Wang, Y. Wang, X. Wu, Y. Tian, W. Yang, and L. Van Gool, DiffIR: Efficient diffusion model for image restoration, in 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, 2024.","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"ref73","first-page":"76806","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Y.","year":"2023"},{"key":"ref74","unstructured":"Y. Yang, J. Sun, H. Li, and Z. Xu, Deep ADMM-Net for compressive sensing MRI, in Proceedings of NeurIPS, 2016, pp. 10\u201318."},{"key":"ref75","doi-asserted-by":"crossref","unstructured":"J. Zhang and B. Ghanem, ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1828\u20131837.","DOI":"10.1109\/CVPR.2018.00196"},{"key":"ref76","doi-asserted-by":"crossref","unstructured":"J. Zhang, J. Pan, W.S. Lai, R. W. Lau, and M.H. Yang, Learning fully convolutional networks for iterative non-blind deconvolution, in Proceedings of CVPR, 2017, pp. 3817\u20133825.","DOI":"10.1109\/CVPR.2017.737"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref78","doi-asserted-by":"crossref","unstructured":"Y. Zhu, K. Zhang, J. Liang, J. Cao, B. Wen, R. Timofte, and L. Van Gool, Denoising diffusion models for plug-and-play image restoration, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023, pp. 1219\u20131229.","DOI":"10.1109\/CVPRW59228.2023.00129"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/24M1688321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:32:05Z","timestamp":1787322725000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1688321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":78,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1137\/24M1688321"],"URL":"https:\/\/doi.org\/10.1137\/24m1688321","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]}}}