{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:09:54Z","timestamp":1777655394564,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"UKRI EPSRC"},{"name":"French government"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Score-based diffusion methods provide a powerful strategy to solve image restoration tasks by flexibly combining a pre-trained foundational prior model with a likelihood function specified during test time . Such methods are predominantly derived from two stochastic processes: reversing Ornstein\u2013Uhlenbeck, which underpins the celebrated denoising diffusion probabilistic models (DDPM) and denoising diffusion implicit models (DDIM), and the Langevin diffusion process. The solutions delivered by DDPM and DDIM are often remarkably realistic, but they are not always consistent with measurements because of likelihood intractability issues and the associated required approximations. Alternatively, using a Langevin process circumvents the intractable likelihood issue, but usually leads to restoration results of inferior quality. This paper presents a novel and highly computationally efficient image restoration method that carefully embeds a foundational DDPM denoiser within an empirical Bayesian Langevin algorithm, which jointly calibrates key model hyper-parameters as it estimates the model\u2019s posterior mean. Extensive experimental results on three canonical tasks (image deblurring, super-resolution, and inpainting) demonstrate that the proposed approach improves on state-of-the-art strategies both in image estimation accuracy and computing time.<\/jats:p>","DOI":"10.1007\/s10851-025-01265-7","type":"journal-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T07:05:30Z","timestamp":1757142330000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Empirical Bayesian Image Restoration by Langevin Sampling with a Denoising Diffusion Implicit Prior"],"prefix":"10.1007","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6437-3670","authenticated-orcid":false,"given":"Charlesquin","family":"Kemajou\u00a0Mbakam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0372-9329","authenticated-orcid":false,"given":"Jean-Francois","family":"Giovannelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6438-6772","authenticated-orcid":false,"given":"Marcelo","family":"Pereyra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,6]]},"reference":[{"key":"1265_CR1","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Advances in Neural Information processing systems 32 (2019)"},{"key":"1265_CR2","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1265_CR3","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising Diffusion Implicit Models. In: International conference on learning representations (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"1265_CR4","first-page":"12438","volume":"33","author":"Y Song","year":"2020","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. Adv. Neural. Inf. Process. Syst. 33, 12438\u201312448 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1265_CR5","unstructured":"Song, Y., Sohl-Dickstein, J.N., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-Based generative modeling through stochastic differential equations. ICLR (2021)"},{"key":"1265_CR6","doi-asserted-by":"crossref","unstructured":"Chung, H., Sim, B., Ye, J.C.: 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, pp. 12413\u201312422 (2022)","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"1265_CR7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., Yang, Y., Chang, M., Chen, S., Feng, H., Xu, Z., Li, Q., Chen, Y.: Srdiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"issue":"12","key":"1265_CR8","doi-asserted-by":"publisher","first-page":"3524","DOI":"10.1109\/TMI.2023.3290149","volume":"42","author":"M \u00d6zbey","year":"2023","unstructured":"\u00d6zbey, M., Dalmaz, O., Dar, S.U., Bedel, H.A., \u00d6zturk, \u015e, G\u00fcng\u00f6r, A., \u00c7ukur, T.: Unsupervised medical image translation with adversarial diffusion models. IEEE Trans. Med. Imag. 42(12), 3524\u20133539 (2023)","journal-title":"IEEE Trans. Med. Imag."},{"key":"1265_CR9","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1265_CR10","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., Norouzi, M.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"issue":"4","key":"1265_CR11","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1265_CR12","unstructured":"Song, J., Vahdat, A., Mardani, M., Kautz, J.: Pseudoinverse-guided diffusion models for inverse problems. In: International conference on learning representations (2022)"},{"key":"1265_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, K., Liang, J., Cao, J., Wen, B., Timofte, R., Van\u00a0Gool, L.: Denoising Diffusion Models for Plug-and-Play Image Restoration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1219\u20131229 (2023)","DOI":"10.1109\/CVPRW59228.2023.00129"},{"key":"1265_CR14","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. Adv. Neural. Inf. Process. Syst. 35, 23593\u201323606 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1265_CR15","doi-asserted-by":"crossref","unstructured":"Coeurdoux, F., Dobigeon, N., Chainais, P.: Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inference. arXiv preprint arXiv:2304.11134 (2023)","DOI":"10.1109\/TIP.2024.3404338"},{"key":"1265_CR16","doi-asserted-by":"crossref","unstructured":"Laroche, C., Almansa, A., Coupete, E.: Fast diffusion EM: a diffusion model for blind inverse problems with application to deconvolution. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 5271\u20135281 (2024)","DOI":"10.1109\/WACV57701.2024.00519"},{"key":"1265_CR17","doi-asserted-by":"crossref","unstructured":"Chung, H., Kim, J., Kim, S., Ye, J.C.: Parallel diffusion models of operator and image for blind inverse problems. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6059\u20136069 (2023)","DOI":"10.1109\/CVPR52729.2023.00587"},{"issue":"2","key":"1265_CR18","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1137\/21M1406349","volume":"15","author":"R Laumont","year":"2022","unstructured":"Laumont, R., Bortoli, V.D., Almansa, A., Delon, J., Durmus, A., Pereyra, M.: Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie. SIAM J. Imag. Sci. 15(2), 701\u2013737 (2022)","journal-title":"SIAM J. Imag. Sci."},{"issue":"4","key":"1265_CR19","doi-asserted-by":"publisher","first-page":"1945","DOI":"10.1137\/20M1339829","volume":"13","author":"AF Vidal","year":"2020","unstructured":"Vidal, A.F., De Bortoli, V., Pereyra, M., Durmus, A.: Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part I: Methodology and experiments. SIAM J. Imag. Sci. 13(4), 1945\u20131989 (2020)","journal-title":"SIAM J. Imag. Sci."},{"key":"1265_CR20","unstructured":"Chen, S., Daras, G., Dimakis, A.: Restoration-degradation beyond linear diffusions: a non-asymptotic analysis for DDIM-type samplers. In: International conference on machine learning. PMLR, pp. 4462\u20134484 (2023)"},{"key":"1265_CR21","unstructured":"Benton, J., Bortoli, V.D., Doucet, A., Deligiannidis, G.: Linear convergence bounds for diffusion models via stochastic localization. In: The Twelfth international conference on learning representations (2024). https:\/\/openreview.net\/forum?id=r5njV3BsuD"},{"issue":"3","key":"1265_CR22","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0304-4149(82)90051-5","volume":"12","author":"BD Anderson","year":"1982","unstructured":"Anderson, B.D.: Reverse-time diffusion equation models. Stoch. Process. Appl. 12(3), 313\u2013326 (1982)","journal-title":"Stoch. Process. Appl."},{"key":"1265_CR23","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. Advances in Neural Information processing systems 31 (2018)"},{"key":"1265_CR24","volume-title":"The Bayesian Choice: from decision-theoretic foundations to computational implementation","author":"CP Robert","year":"2007","unstructured":"Robert, C.P.: The Bayesian Choice: from decision-theoretic foundations to computational implementation. Springer, New York (2007)"},{"key":"1265_CR25","unstructured":"Cardoso, G., Janati El Idrissi, Y., Moulines, E., Corff, S.L.: Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems. In: The Twelfth International conference on learning representations (2024). https:\/\/openreview.net\/forum?id=nHESwXvxWK"},{"issue":"1","key":"1265_CR26","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1137\/16M1108340","volume":"11","author":"A Durmus","year":"2018","unstructured":"Durmus, A., Moulines, E., Pereyra, M.: Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau. SIAM J. Imag. Sci. 11(1), 473\u2013506 (2018)","journal-title":"SIAM J. Imag. Sci."},{"key":"1265_CR27","unstructured":"Laumont, R.: Bayesian computation with Plug & Play priors for inverse problems in imaging sciences. Theses, Universit\u00e9 Paris Cit\u00e9 (November 2022). https:\/\/theses.hal.science\/tel-03981427"},{"key":"1265_CR28","doi-asserted-by":"crossref","unstructured":"Terris, M., Moreau, T., Pustelnik, N., Tachella, J.: Equivariant Plug-and-Play image reconstruction. arXiv:2312.01831 (2023)","DOI":"10.1109\/CVPR52733.2024.02386"},{"key":"1265_CR29","unstructured":"Klatzer, T., Melidonis, S., Pereyra, M., Zygalakis, K.C.: Efficient Bayesian computation using plug-and-play priors for poisson inverse problems (2025). arXiv:2503.16222"},{"key":"1265_CR30","doi-asserted-by":"crossref","unstructured":"Renaud, M., Leclaire, A., Papadakis, N.: Equivariant denoisers for image restoration. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp. 227\u2013240 (2025). Springer","DOI":"10.1007\/978-3-031-92366-1_18"},{"key":"1265_CR31","doi-asserted-by":"crossref","unstructured":"Serre, J.-P.: Linear representations of finite groups, volume 42 of. Graduate texts in Mathematics, 80 (1977)","DOI":"10.1007\/978-1-4684-9458-7"},{"issue":"159","key":"1265_CR32","first-page":"1","volume":"17","author":"SJ Vollmer","year":"2016","unstructured":"Vollmer, S.J., Zygalakis, K.C., Teh, Y.W.: Exploration of the (non-) asymptotic bias and variance of stochastic gradient Langevin dynamics. J. Mach. Learn. Res. 17(159), 1\u201348 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"1265_CR33","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1137\/22M1506122","volume":"16","author":"M Pereyra","year":"2023","unstructured":"Pereyra, M., Vargas-Mieles, L.A., Zygalakis, K.C.: The split Gibbs sampler revisited: improvements to its algorithmic structure and augmented target distribution. SIAM J. Imag. Sci. 16(4), 2040\u20132071 (2023)","journal-title":"SIAM J. Imag. Sci."},{"key":"1265_CR34","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1265_CR35","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1051\/0004-6361\/201219950","volume":"549","author":"F Orieux","year":"2013","unstructured":"Orieux, F., Giovannelli, J.-F., Rodet, T., Abergel, A.: Estimating hyperparameters and instrument parameters in regularized inversion illustration for herschel\/spire map making. Astron. Astrophys. 549, 83 (2013)","journal-title":"Astron. Astrophys."},{"key":"1265_CR36","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1265_CR37","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"10","key":"1265_CR38","doi-asserted-by":"publisher","first-page":"6360","DOI":"10.1109\/TPAMI.2021.3088914","volume":"44","author":"K Zhang","year":"2021","unstructured":"Zhang, K., Li, Y., Zuo, W., Zhang, L., Van Gool, L., Timofte, R.: Plug-and-play image restoration with deep denoiser prior. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6360\u20136376 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"1265_CR39","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"1265_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"4","key":"1265_CR41","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.1137\/20M1339842","volume":"13","author":"V De Bortoli","year":"2020","unstructured":"De Bortoli, V., Durmus, A., Pereyra, M., Vidal, A.F.: Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part II: Theoretical analysis. SIAM J. Imag. Sci. 13(4), 1990\u20132028 (2020)","journal-title":"SIAM J. Imag. Sci."},{"issue":"2","key":"1265_CR42","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1137\/23M1584496","volume":"17","author":"CK Mbakam","year":"2024","unstructured":"Mbakam, C.K., Pereyra, M., Giovannelli, J.-F.: Marginal likelihood estimation in semiblind Image deconvolution: a stochastic approximation approach. SIAM J. Imag. Sci. 17(2), 1206\u20131254 (2024)","journal-title":"SIAM J. Imag. Sci."},{"issue":"3","key":"1265_CR43","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1137\/22M1502240","volume":"16","author":"S Melidonis","year":"2023","unstructured":"Melidonis, S., Dobson, P., Altmann, Y., Pereyra, M., Zygalakis, K.: Efficient Bayesian computation for low-photon imaging problems. SIAM J. Imag. Sci. 16(3), 1195\u20131234 (2023)","journal-title":"SIAM J. Imag. Sci."}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-025-01265-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10851-025-01265-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-025-01265-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:02:28Z","timestamp":1761962548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10851-025-01265-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,6]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1265"],"URL":"https:\/\/doi.org\/10.1007\/s10851-025-01265-7","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"value":"0924-9907","type":"print"},{"value":"1573-7683","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,6]]},"assertion":[{"value":"8 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"50"}}