{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:33:24Z","timestamp":1781199204701,"version":"3.54.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T00:00:00Z","timestamp":1572393600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T00:00:00Z","timestamp":1572393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["GRK 2224\/1"],"award-info":[{"award-number":["GRK 2224\/1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["276397488"],"award-info":[{"award-number":["276397488"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Grant","award":["765374"],"award-info":[{"award-number":["765374"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2020,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n<jats:p>The present paper studies so-called deep image prior (DIP) techniques in the context of ill-posed inverse problems. DIP networks have been recently introduced for applications in image processing; also first experimental results for applying DIP to inverse problems have been reported. This paper aims at discussing different interpretations of DIP and to obtain analytic results for specific network designs and linear operators. The main contribution is to introduce the idea of viewing these approaches as the optimization of Tikhonov functionals rather than optimizing networks. Besides theoretical results, we present numerical verifications.\n<\/jats:p>","DOI":"10.1007\/s10851-019-00923-x","type":"journal-article","created":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T22:05:50Z","timestamp":1572473150000},"page":"456-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":81,"title":["Regularization by Architecture: A Deep Prior Approach for Inverse Problems"],"prefix":"10.1007","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2919-4956","authenticated-orcid":false,"given":"S\u00f6ren","family":"Dittmer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Kluth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Maass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6550-6043","authenticated-orcid":false,"given":"Daniel","family":"Otero\u00a0Baguer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,10,30]]},"reference":[{"key":"923_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). \nhttps:\/\/www.tensorflow.org\/\n\n. Software available from tensorflow.org"},{"issue":"6","key":"923_CR2","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/TMI.2018.2799231","volume":"37","author":"J Adler","year":"2018","unstructured":"Adler, J., \u00d6ktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imaging 37(6), 1322\u20131332 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"923_CR3","unstructured":"Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M.W., Pfau, D., Schaul, T., Shillingford, B., De\u00a0Freitas, N.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981\u20133989 (2016)"},{"key":"923_CR4","unstructured":"Anonymous: on the spectral bias of neural networks. In: Submitted to International Conference on Learning Representations (under review) (2019). \nhttps:\/\/openreview.net\/forum?id=r1gR2sC9FX\n\n. Accessed 28 Oct 2019"},{"key":"923_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0962492919000059","volume":"28","author":"S Arridge","year":"2019","unstructured":"Arridge, S., Maass, P., \u00d6ktem, O., Sch\u00f6nlieb, C.B.: Solving inverse problems using data-driven models. Acta Numer. 28, 1\u2013174 (2019)","journal-title":"Acta Numer."},{"issue":"1","key":"923_CR6","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/080716542","volume":"2","author":"A Beck","year":"2009","unstructured":"Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183\u2013202 (2009). \nhttps:\/\/doi.org\/10.1137\/080716542","journal-title":"SIAM J. Imaging Sci."},{"key":"923_CR7","unstructured":"Bora, A., Jalal, A., Price, E., Dimakis, A.G.: Compressed sensing using generative models. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6\u201311 August 2017, pp. 537\u2013546 (2017). \nhttp:\/\/proceedings.mlr.press\/v70\/bora17a.html"},{"issue":"8","key":"923_CR8","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","volume":"35","author":"J Bruna","year":"2013","unstructured":"Bruna, J., Mallat, S.: Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872\u20131886 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"923_CR9","unstructured":"Chen, X., Liu, J., Wang, Z., Yin, W.: Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds. In: Advances in Neural Information Processing Systems, pp. 9061\u20139071 (2018)"},{"key":"923_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Gadelha, M., Maji, S., Sheldon, D.: A Bayesian perspective on the deep image prior. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00559"},{"issue":"4","key":"923_CR11","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1137\/050626090","volume":"4","author":"P Combettes","year":"2005","unstructured":"Combettes, P., Wajs, V.: Signal recovery by proximal forward\u2013backward splitting. Multiscale Model. Simul. 4(4), 1168\u20131200 (2005). \nhttps:\/\/doi.org\/10.1137\/050626090","journal-title":"Multiscale Model. Simul."},{"issue":"11","key":"923_CR12","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1002\/cpa.20042","volume":"57","author":"I Daubechies","year":"2004","unstructured":"Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57(11), 1413\u20131457 (2004). \nhttps:\/\/doi.org\/10.1002\/cpa.20042","journal-title":"Commun. Pure Appl. Math."},{"key":"923_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8","volume-title":"Regularization of Inverse Problems, Mathematics and Its Applications","author":"HW Engl","year":"1996","unstructured":"Engl, H.W., Hanke, M., Neubauer, A.: Regularization of Inverse Problems, Mathematics and Its Applications, vol. 375. Kluwer Academic Publishers Group, Dordrecht (1996)"},{"issue":"30","key":"923_CR14","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.1162\/neco_a_01100","volume":"8","author":"D Forster","year":"2018","unstructured":"Forster, D., Sheikh, A.S., L\u00fccke, J.: Neural simpletrons: learning in the limit of few labels with directed generative networks. Neural Comput. 8(30), 2113\u20132174 (2018)","journal-title":"Neural Comput."},{"issue":"7","key":"923_CR15","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1109\/TSP.2018.2791945","volume":"66","author":"R Giryes","year":"2018","unstructured":"Giryes, R., Eldar, Y.C., Bronstein, A.M., Sapiro, G.: Tradeoffs between convergence speed and reconstruction accuracy in inverse problems. IEEE Trans. Signal Process. 66(7), 1676\u20131690 (2018)","journal-title":"IEEE Trans. Signal Process."},{"key":"923_CR16","unstructured":"Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: ICML 2010\u2014Proceedings, 27th International Conference on Machine Learning, pp. 399\u2013406 (2010)"},{"issue":"6","key":"923_CR17","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/TMI.2018.2820382","volume":"37","author":"A Hauptmann","year":"2018","unstructured":"Hauptmann, A., Lucka, F., Betcke, M., Huynh, N., Adler, J., Cox, B., Beard, P., Ourselin, S., Arridge, S.: Model-based learning for accelerated, limited-view 3-d photoacoustic tomography. IEEE Trans. Med. Imaging 37(6), 1382\u20131393 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"9","key":"923_CR18","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","volume":"26","author":"KH Jin","year":"2017","unstructured":"Jin, K.H., McCann, M.T., Froustey, E., Unser, M.: Deep convolutional neural network for inverse problems in imaging. IEEE Trans. Image Process. 26(9), 4509\u20134522 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"923_CR19","doi-asserted-by":"publisher","unstructured":"Lempitsky, V., Vedaldi, A., Ulyanov, D.: Deep image prior. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9446\u20139454 (2018). \nhttps:\/\/doi.org\/10.1109\/CVPR.2018.00984","DOI":"10.1109\/CVPR.2018.00984"},{"key":"923_CR20","unstructured":"Liu, J., Chen, X., Wang, Z., Yin, W.: ALISTA: analytic weights are as good as learned weights in LISTA. In: International Conference on Learning Representations (2019). \nhttps:\/\/openreview.net\/forum?id=B1lnzn0ctQ"},{"key":"923_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-322-84808-6","volume-title":"Inverse und Schlecht Gestellte Probleme","author":"AK Louis","year":"1989","unstructured":"Louis, A.K.: Inverse und Schlecht Gestellte Probleme. Vieweg+Teubner Verlag, Wiesbaden (1989)"},{"key":"923_CR22","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-319-73074-5_6","volume-title":"Deep Learning for Trivial Inverse Problems","author":"P Maass","year":"2019","unstructured":"Maass, P.: Deep Learning for Trivial Inverse Problems, pp. 195\u2013209. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-319-73074-5_6"},{"key":"923_CR23","unstructured":"Mataev, G., Elad, M., Milanfar, P.: Deepred: deep image prior powered by red (2019). arXiv preprint \narXiv:1903.10176"},{"key":"923_CR24","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., M\u00f6ller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: IEEE International Conference on Computer Vision, pp. 1781\u20131790 (2017)","DOI":"10.1109\/ICCV.2017.198"},{"key":"923_CR25","unstructured":"Moreau, T., Bruna, J.: Understanding trainable sparse coding via matrix factorization (2016). arXiv preprint \narXiv:1609.00285"},{"key":"923_CR26","unstructured":"Nesterov, Y.: Lectures on Convex Optimization. Springer Optimization and Its Applications. Springer(2019). \nhttps:\/\/books.google.de\/books?id=JSyNtQEACAAJ"},{"issue":"4","key":"923_CR27","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MSP.2018.2820224","volume":"35","author":"V Papyan","year":"2018","unstructured":"Papyan, V., Romano, Y., Sulam, J., Elad, M.: Theoretical foundations of deep learning via sparse representations: a multilayer sparse model and its connection to convolutional neural networks. IEEE Signal Process. Mag. 35(4), 72\u201389 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"923_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-322-80234-7","volume-title":"Keine Probleme mit inversen Problemen: eine Einf\u00fchhrung in ihre stabile L\u00f6sung","author":"A Rieder","year":"2003","unstructured":"Rieder, A.: Keine Probleme mit inversen Problemen: eine Einf\u00fchhrung in ihre stabile L\u00f6sung. Vieweg, Wiesbaden (2003)"},{"key":"923_CR29","unstructured":"Saxe, A.M., McClelland, J.L., Ganguli, S.: Exact solutions to the nonlinear dynamics of learning in deep linear neural networks (2013). arXiv preprint \narXiv:1312.6120"},{"issue":"9","key":"923_CR30","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1109\/TPAMI.2015.2392779","volume":"37","author":"P Sprechmann","year":"2015","unstructured":"Sprechmann, P., Bronstein, A.M., Sapiro, G.: Learning efficient sparse and low rank models. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1821\u20131833 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"923_CR31","unstructured":"Sulam, J., Aberdam, A., Beck, A., Elad, M.: On multi-layer basis pursuit, efficient algorithms and convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. (2019). arXiv preprint \narXiv:1806.00701"},{"key":"923_CR32","unstructured":"Van\u00a0Veen, D., Jalal, A., Price, E., Vishwanath, S., Dimakis, A.G.: Compressed sensing with deep image prior and learned regularization (2018). arXiv preprint \narXiv:1806.06438"},{"key":"923_CR33","doi-asserted-by":"crossref","unstructured":"Vonesch, C., Unser, M.: A fast iterative thresholding algorithm for wavelet-regularized deconvolution - art. no. 67010d. In: Wavelets Xii, Pts 1 And 2, vol. 6701, pp. D7010\u2013D7010 (2007)","DOI":"10.1117\/12.733532"},{"key":"923_CR34","unstructured":"Xin, B., Wang, Y., Gao, W., Wipf, D., Wang, B.: Maximal sparsity with deep networks? In: Advances in Neural Information Processing Systems, pp. 4340\u20134348 (2016)"},{"key":"923_CR35","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization (2016). arXiv preprint \narXiv:1611.03530"}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00923-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10851-019-00923-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00923-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T00:15:30Z","timestamp":1603930530000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10851-019-00923-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,30]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["923"],"URL":"https:\/\/doi.org\/10.1007\/s10851-019-00923-x","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"value":"0924-9907","type":"print"},{"value":"1573-7683","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,30]]},"assertion":[{"value":"30 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}