{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:03:12Z","timestamp":1784566992079,"version":"3.55.0"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100008332","name":"Graz University of Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100008332","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Diffusion models play an important role in many state-of-the-art algorithms to solve inverse problems in imaging. In particular, reconstructing MRI and CT images from undersampled data can be reformulated as a canonical inverse problem that benefits from strong priors. Researchers typically re-purpose models originally designed for unconditional sampling without modifications and achieve remarkable accuracy on in-distribution (ID) reconstruction. However, due to the scarce availability of training data and the large number of different imaging setups, increasing the generalization capabilities of diffusion-based priors is key to clinical adoption. To do so, we propose two solutions: (i) using smaller models and (ii) training on natural images. Using three different posterior sampling algorithms, we evaluate the influence of network size and training data. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on ID reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, outperforming models trained on medical images in OOD cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task.<\/jats:p>","DOI":"10.1007\/s11263-026-02904-1","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T08:11:56Z","timestamp":1780560716000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bigger Isn\u2019t Always Better: Towards a General Prior for Medical Image Reconstruction"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4798-1725","authenticated-orcid":false,"given":"Lukas","family":"Glaszner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1941-875X","authenticated-orcid":false,"given":"Martin","family":"Zach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6120-1058","authenticated-orcid":false,"given":"Thomas","family":"Pock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"issue":"2","key":"2904_CR1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TMI.2018.2865356","volume":"38","author":"HK Aggarwal","year":"2019","unstructured":"Aggarwal, H. K., Mani, M. P., & Jacob, M. (2019). MoDL: Model-based deep learning architecture for inverse problems. IEEE Transactions on Medical Imaging, 38(2), 394\u2013405. https:\/\/doi.org\/10.1109\/TMI.2018.2865356","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"3","key":"2904_CR2","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. (1982). Reverse-time diffusion equation models. Stochastic Processes and their Applications, 12(3), 313\u2013326. https:\/\/doi.org\/10.1016\/0304-4149(82)90051-5","journal-title":"Stochastic Processes and their Applications"},{"key":"2904_CR3","doi-asserted-by":"publisher","unstructured":"Araujo, A., Norris, W., Sim, J. (2019). Computing receptive fields of convolutional neural networks. Distill, 4(11), 21, https:\/\/doi.org\/10.23915\/distill.00021","DOI":"10.23915\/distill.00021"},{"key":"2904_CR4","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. Proceedings of the 34th international conference on machine learning (Vol. 70, pp. 214\u2013223) PMLR."},{"key":"2904_CR5","doi-asserted-by":"publisher","unstructured":"Biroli, G., Bonnaire, T., Bortoli, V.d., & M\u00e9zard, M. (2024). Dynamical regimes of diffusion models. Nature Communications,15(1), 9957. https:\/\/doi.org\/10.1038\/s41467-024-54281-3","DOI":"10.1038\/s41467-024-54281-3"},{"key":"2904_CR6","unstructured":"Brendel, W., & Bethge, M. (2019). Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet International conference on learning representations."},{"key":"2904_CR7","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis International conference on learning representations."},{"issue":"3","key":"2904_CR8","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:VISI.0000045324.43199.43","volume":"61","author":"A Bruhn","year":"2005","unstructured":"Bruhn, A., Weickert, J., & Schn\u00f6rr, C. (2005). Lucas\/kanade meets horn\/schunck: Combining local and global optic flow methods. International Journal of Computer Vision, 61(3), 211\u2013231. https:\/\/doi.org\/10.1023\/B:VISI.0000045324.43199.43","journal-title":"International Journal of Computer Vision"},{"key":"2904_CR9","unstructured":"Carlini, N., Hayes, J., Nasr, M., Jagielski, M., Sehwag, V., Tram\u00e8r, F., & Wallace, E. (2023). Extracting training data from diffusion models. 32nd USENIX security symposium (USENIX security 23) (pp. 5253\u20135270). Anaheim, CA: USENIX Association."},{"issue":"2","key":"2904_CR10","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/83.551699","volume":"6","author":"P Charbonnier","year":"1997","unstructured":"Charbonnier, P., Blanc-Feraud, L., Aubert, G., & Barlaud, M. (1997). Deterministic edge-preserving regularization in computed imaging. IEEE Transactions on Image Processing, 6(2), 298\u2013311. https:\/\/doi.org\/10.1109\/83.551699","journal-title":"IEEE Transactions on Image Processing"},{"key":"2904_CR11","unstructured":"Chung, H., Kim, J., Mccann, M. T., Klasky, M. L., & Ye, J. C. (2023). Diffusion posterior sampling for general noisy inverse problems International conference on learning representations."},{"key":"2904_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102479","volume":"80","author":"H Chung","year":"2022","unstructured":"Chung, H., & Ye, J. C. (2022). Score-based diffusion models for accelerated MRI. Medical Image Analysis, 80, Article 102479. https:\/\/doi.org\/10.1016\/j.media.2022.102479","journal-title":"Medical Image Analysis"},{"issue":"496","key":"2904_CR13","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1198\/jasa.2011.tm11181","volume":"106","author":"B Efron","year":"2011","unstructured":"Efron, B. (2011). Tweedie\u2019s formula and selection bias. Journal of the American Statistical Association, 106(496), 1602\u20131614. https:\/\/doi.org\/10.1198\/jasa.2011.tm11181","journal-title":"Journal of the American Statistical Association"},{"key":"2904_CR14","doi-asserted-by":"crossref","unstructured":"Gao, S., Liu, X., Zeng, B., Xu, S., Li, Y., Luo, X., & Zhang, B. (2023). Implicit diffusion models for continuous super-resolution. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10021\u201310030)","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"2904_CR15","unstructured":"Gao, Z., & Zhou, S. K. (2024). U$$^2$$MRPD: Unsupervised undersampled MRI reconstruction by prompting a large latent diffusion model"},{"issue":"1","key":"2904_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S Geman","year":"1992","unstructured":"Geman, S., Bienenstock, E., & Doursat, R. (1992). Neural networks and the bias\/variance dilemma. Neural Computation, 4(1), 1\u201358. https:\/\/doi.org\/10.1162\/neco.1992.4.1.1","journal-title":"Neural Computation"},{"key":"2904_CR17","doi-asserted-by":"crossref","unstructured":"Glaszner, L., & Zach, M. (2025). Bigger isn\u2019t always better: Towards a general prior for medical image reconstruction. Pattern recognition: 46th DAGM german conference, DAGM GCPR 2024, munich, germany, september 10\u201313, 2024, proceedings, part i (pp. 275\u2013291).","DOI":"10.1007\/978-3-031-85181-0_18"},{"key":"2904_CR18","unstructured":"Gu, X., Du, C., Pang, T., Li, C., Lin, M., Wang, Y. (2025). On memorization in diffusion models."},{"key":"2904_CR19","unstructured":"Gupta, S., Jalal, A., Parulekar, A., Price, E., & Xun, Z. (2024). Diffusion posterior sampling is computationally intractable. Proceedings of the 41st international conference on machine learning. JMLR.org"},{"issue":"4","key":"2904_CR20","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.202470004","volume":"47","author":"A Habring","year":"2024","unstructured":"Habring, A., & Holler, M. (2024). Neural-network-based regularization methods for inverse problems in imaging. GAMM-Mitteilungen, 47(4), Article e202470004. https:\/\/doi.org\/10.1002\/gamm.202470004","journal-title":"GAMM-Mitteilungen"},{"issue":"6","key":"2904_CR21","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","volume":"79","author":"K Hammernik","year":"2018","unstructured":"Hammernik, K., Klatzer, T., Kobler, E., Recht, M. P., Sodickson, D. K., Pock, T., & Knoll, F. (2018). Learning a variational network for reconstruction of accelerated MRI data. Magnetic Resonance in Medicine, 79(6), 3055\u20133071. https:\/\/doi.org\/10.1002\/mrm.26977","journal-title":"Magnetic Resonance in Medicine"},{"key":"2904_CR22","doi-asserted-by":"publisher","unstructured":"Hooper, S.M., Dunnmon, J.A., Lungren, M.P., Mastrodicasa, D., Rubin, D.L., R\u00e9, C.. Patel, B.N. (2021). Impact of upstream medical image processing on downstream performance of a head CT triage neural network. Radiology: Artificial Intelligence, 3(4), e200229, https:\/\/doi.org\/10.1148\/ryai.2021200229","DOI":"10.1148\/ryai.2021200229"},{"key":"2904_CR23","doi-asserted-by":"crossref","unstructured":"Huang, J., & Mumford, D. (1999). Statistics of natural images and models. Proceedings. 1999 IEEE computer society conference on computer vision and pattern recognition (cat. no pr00149) (Vol. 1, pp. 541\u2013547)","DOI":"10.1109\/CVPR.1999.786990"},{"issue":"24","key":"2904_CR24","first-page":"695","volume":"6","author":"A Hyv\u00e4rinen","year":"2005","unstructured":"Hyv\u00e4rinen, A. (2005). Estimation of non-normalized statistical models by score matching. Journal of Machine Learning Research, 6(24), 695\u2013709.","journal-title":"Journal of Machine Learning Research"},{"key":"2904_CR25","unstructured":"Jalal, A., Arvinte, M., Daras, G., Price, E., Dimakis, A. G., & Tamir, J. (2021). Robust compressed sensing MRI with deep generative priors. Advances in neural information processing systems (Vol. 34, pp. 14938\u201314954). Curran Associates Inc."},{"key":"2904_CR26","unstructured":"Kamb, M., & Ganguli, S. (2025). An analytic theory of creativity in convolutional diffusion models. Forty-second international conference on machine learning"},{"key":"2904_CR27","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of GANs for improved quality, stability, and variation International conference on learning representations."},{"key":"2904_CR28","doi-asserted-by":"crossref","unstructured":"Kawar, B., Elad, M., Ermon, S., & Song, J. (2022). Denoising diffusion restoration models. Advances in neural information processing systems (Vol. 35, pp. 23593\u201323606). Curran Associates Inc.","DOI":"10.52202\/068431-1714"},{"key":"2904_CR29","unstructured":"Kawar, B., Vaksman, G., & Elad, M. (2021). SNIPS: Solving noisy inverse problems stochastically. Advances in neural information processing systems (Vol. 34, pp. 21757\u201321769). Curran Associates Inc."},{"issue":"11","key":"2904_CR30","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1109\/TMI.2025.3575071","volume":"44","author":"A Khorashadizadeh","year":"2025","unstructured":"Khorashadizadeh, A., Debarnot, V., Liu, T., & Dokmanic, I. (2025). GLIMPSE: Generalized locality for scalable and robust CT. IEEE Transactions on Medical Imaging, 44(11), 4335\u20134349. https:\/\/doi.org\/10.1109\/TMI.2025.3575071","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2904_CR31","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1109\/TCI.2025.3594983","volume":"11","author":"A Khorashadizadeh","year":"2025","unstructured":"Khorashadizadeh, A., Liaudat, T. I., Liu, T., McEwen, J. D., & Dokmanic, I. (2025). LoFi: Neural local fields for scalable image reconstruction. IEEE Transactions on Computational Imaging, 11, 1128\u20131141. https:\/\/doi.org\/10.1109\/TCI.2025.3594983","journal-title":"IEEE Transactions on Computational Imaging"},{"key":"2904_CR32","unstructured":"Kingma, D. P., & Ba, J. (2017). Adam: A method for stochastic optimization"},{"issue":"2","key":"2904_CR33","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/mrm.22595","volume":"65","author":"F Knoll","year":"2011","unstructured":"Knoll, F., Bredies, K., Pock, T., & Stollberger, R. (2011). Second order total generalized variation (TGV) for MRI. Magnetic Resonance in Medicine, 65(2), 480\u2013491. https:\/\/doi.org\/10.1002\/mrm.22595","journal-title":"Magnetic Resonance in Medicine"},{"key":"2904_CR34","doi-asserted-by":"publisher","unstructured":"Knoll, F., Zbontar, J., Sriram, A., Muckley, M.J., Bruno, M., Defazio, A.. others (2020). fastMRI: A publicly available raw k-space and dicom dataset of knee images for accelerated mr image reconstruction using machine learning. Radiology: Artificial Intelligence, 2(1), e190007, https:\/\/doi.org\/10.1148\/ryai.202019007","DOI":"10.1148\/ryai.202019007"},{"key":"2904_CR35","unstructured":"Le, H., & Borji, A. (2018). What are the receptive, effective receptive, and projective fields of neurons in convolutional neural networks?"},{"key":"2904_CR36","doi-asserted-by":"crossref","unstructured":"Lee, S., Chung, H., Park, M., Park, J., Ryu, W.-S., Ye, J.C. (2023). Improving 3d imaging with pre-trained perpendicular 2d diffusion models. Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 10710\u201310720).","DOI":"10.1109\/ICCV51070.2023.00983"},{"key":"2904_CR37","doi-asserted-by":"publisher","unstructured":"Leuschner, J., Schmidt, M., Baguer, D.O., Maass, P. (2021). LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction. Scientific Data, 8(1), , https:\/\/doi.org\/10.1038\/s41597-021-00893-z","DOI":"10.1038\/s41597-021-00893-z"},{"key":"2904_CR38","unstructured":"Lin, K., & Heckel, R. (2024). Robustness of deep learning for accelerated MRI: Benefits of diverse training data. Proceedings of the 41st international conference on machine learning (Vol. 235, pp. 30018\u201330041) PMLR."},{"key":"2904_CR39","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., & Van Gool, L. (2022). Repaint: Inpainting using denoising diffusion probabilistic models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 11461\u201311471)","DOI":"10.1109\/CVPR52688.2022.01117"},{"issue":"2299","key":"2904_CR40","doi-asserted-by":"publisher","first-page":"20240323","DOI":"10.1098\/rsta.2024.0323","volume":"383","author":"G Luo","year":"2025","unstructured":"Luo, G., Wang, X., Blumenthal, M., Schilling, M., Kotikalapudi, R., Rauf, E., & Uecker, M. (2025). Generative priors for mri reconstruction trained from magnitude-only images using phase augmentation. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 383(2299), 20240323. https:\/\/doi.org\/10.1098\/rsta.2024.0323","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"key":"2904_CR41","unstructured":"Luo, W., Li, Y., Urtasun, R., & Zemel, R. (2016). Understanding the effective receptive field in deep convolutional neural networks. Advances in neural information processing systems (Vol. 29,. Curran Associates Inc."},{"issue":"6","key":"2904_CR42","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1002\/mrm.21391","volume":"58","author":"M Lustig","year":"2007","unstructured":"Lustig, M., Donoho, D., & Pauly, J. M. (2007). Sparse MRI: The application of compressed sensing for rapid mr imaging. Magnetic Resonance in Medicine, 58(6), 1182\u20131195. https:\/\/doi.org\/10.1002\/mrm.21391","journal-title":"Magnetic Resonance in Medicine"},{"key":"2904_CR43","doi-asserted-by":"crossref","unstructured":"Nagler, L., Zach, M., & Pock, T. (2025). Product of gaussian mixture diffusion model for non-linear MRI inversion. Scale space and variational methods in computer vision (pp. 146\u2013158)","DOI":"10.1007\/978-3-031-92366-1_12"},{"key":"2904_CR44","unstructured":"Neyshabur, B., Bhojanapalli, S., Mcallester, D., & Srebro, N. (2017). Exploring generalization in deep learning. Advances in neural information processing systems (Vol. 30,. Curran Associates Inc."},{"key":"2904_CR45","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., & Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems (Vol. 32,. Curran Associates Inc."},{"key":"2904_CR46","doi-asserted-by":"crossref","unstructured":"Robbins, H. E. (1992). An empirical bayes approach to statistics. Breakthroughs in statistics: Foundations and basic theory (pp. 388\u2013394). New York: Springer.","DOI":"10.1007\/978-1-4612-0919-5_26"},{"key":"2904_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10684\u201310695)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2904_CR48","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention - miccai, 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2904_CR49","unstructured":"Scarvelis, C., de Oc\u00e1riz\u00a0Borde, H.S., Solomon, J. (2025). Closed-form diffusion models."},{"key":"2904_CR50","doi-asserted-by":"crossref","unstructured":"Schlemper, J., Caballero, J., Hajnal, J. V., Price, A., & Rueckert, D. (2017). A deep cascade of convolutional neural networks for mr image reconstruction. Information processing in medical imaging (pp. 647\u2013658). Springer International Publishing.","DOI":"10.1007\/978-3-319-59050-9_51"},{"key":"2904_CR51","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., & Jitsev, J. (2022). LAION-5B: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems (Vol. 35, pp. 25278\u201325294). Curran Associates Inc.","DOI":"10.52202\/068431-1833"},{"key":"2904_CR52","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., & Goldstein, T.2023)a. Diffusion art or digital forgery? investigating data replication in diffusion models. Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (cvpr) (pp. 6048\u20136058)","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"2904_CR53","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., & Goldstein, T.2023)b. Understanding and mitigating copying in diffusion models. Advances in neural information processing systems (pp. 47783\u201347803)","DOI":"10.52202\/075280-2071"},{"key":"2904_CR54","unstructured":"Song, Y., & Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems (Vol. 32,. Curran Associates Inc."},{"key":"2904_CR55","unstructured":"Song, Y., Garg, S., Shi, J., & Ermon, S. (2020). Sliced score matching: A scalable approach to density and score estimation. Proceedings of the 35th uncertainty in artificial intelligence conference (Vol. 115, pp. 574\u2013584) PMLR."},{"key":"2904_CR56","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations International conference on learning representations."},{"key":"2904_CR57","unstructured":"Tancik, M., Srinivasan, P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., & Ng, R. (2020). Fourier features let networks learn high frequency functions in low dimensional domains. Advances in neural information processing systems (Vol. 33, pp. 7537\u20137547). Curran Associates Inc."},{"key":"2904_CR58","unstructured":"Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems (Vol. 30,. Curran Associates Inc."},{"issue":"6","key":"2904_CR59","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/3571070","volume":"66","author":"G Vardi","year":"2023","unstructured":"Vardi, G. (2023). On the implicit bias in deep-learning algorithms. Communications of the ACM, 66(6), 86\u201393. https:\/\/doi.org\/10.1145\/3571070","journal-title":"Communications of the ACM"},{"key":"2904_CR60","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems (Vol. 30)"},{"key":"2904_CR61","doi-asserted-by":"publisher","unstructured":"Vincent, P. (2011). A connection between score matching and denoising autoencoders. Neural Computation,23(7), 1661\u20131674. https:\/\/doi.org\/10.1162\/NECO_a_00142","DOI":"10.1162\/NECO_a_00142"},{"key":"2904_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. Proceedings of the ieee conference on computer vision and pattern recognition (cvpr)","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"12","key":"2904_CR63","doi-asserted-by":"publisher","first-page":"3817","DOI":"10.1109\/TMI.2023.3311345","volume":"42","author":"M Zach","year":"2023","unstructured":"Zach, M., Knoll, F., & Pock, T. (2023). Stable deep MRI reconstruction using generative priors. IEEE Transactions on Medical Imaging, 42(12), 3817\u20133832. https:\/\/doi.org\/10.1109\/TMI.2023.3311345","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"4","key":"2904_CR64","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/s10851-024-01180-3","volume":"66","author":"M Zach","year":"2024","unstructured":"Zach, M., Kobler, E., Chambolle, A., & Pock, T. (2024). Product of gaussian mixture diffusion models. Journal of Mathematical Imaging and Vision, 66(4), 504\u2013528. https:\/\/doi.org\/10.1007\/s10851-024-01180-3","journal-title":"Journal of Mathematical Imaging and Vision"},{"issue":"3","key":"2904_CR65","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021). Understanding deep learning (still) requires rethinking generalization. Communications of the ACM, 64(3), 107\u2013115. https:\/\/doi.org\/10.1145\/3446776","journal-title":"Communications of the ACM"},{"key":"2904_CR66","unstructured":"Zhang, H., Zhou, J., Lu, Y., Guo, M., Wang, P., Shen, L., & Qu, Q. (2024). The emergence of reproducibility and consistency in diffusion models. Forty-first international conference on machine learning"},{"key":"2904_CR67","unstructured":"Zhang, R. (2019). Making convolutional networks shift-invariant again. Proceedings of the 36th international conference on machine learning (Vol. 97, pp. 7324\u20137334) PMLR."},{"key":"2904_CR68","doi-asserted-by":"publisher","unstructured":"Zhao, H., Gallo, O., Frosio, I., & Kautz, J. (2017). Loss functions for image restoration with neural networks. IEEE Transactions on Computational Imaging,3(1), 47\u201357. https:\/\/doi.org\/10.1109\/TCI.2016.2644865","DOI":"10.1109\/TCI.2016.2644865"},{"key":"2904_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, K., Liang, J., Cao, J., Wen, B., Timofte, R., & Van Gool, L. (2023). Denoising diffusion models for plug-and-play image restoration. Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (cvpr) workshops (pp. 1219\u20131229)","DOI":"10.1109\/CVPRW59228.2023.00129"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02904-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02904-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02904-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:14:52Z","timestamp":1784564092000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02904-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":69,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2904"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02904-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"1 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"307"}}