{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T06:40:01Z","timestamp":1749278401407,"version":"3.41.0"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11263-025-02410-w","type":"journal-article","created":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T02:09:11Z","timestamp":1742695751000},"page":"4837-4863","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Preconditioned Score-Based Generative Models"],"prefix":"10.1007","volume":"133","author":[{"given":"Hengyuan","family":"Ma","sequence":"first","affiliation":[]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jianfeng","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,21]]},"reference":[{"key":"2410_CR1","unstructured":"Bao, F., Li, C., Sun, J., Zhu, J., & Zhang, B. (2022). Estimating the optimal covariance with imperfect mean in diffusion probabilistic models."},{"key":"2410_CR2","unstructured":"Bao, F., Li, C., Zhu, J., & Zhang, B. (2022). Analytic-dpm: An analytic estimate of the optimal reverse variance in diffusion probabilistic models. In International Conference on Learning Representations."},{"key":"2410_CR3","unstructured":"Brigham, E. O. (1988). The fast Fourier transform and its applications."},{"key":"2410_CR4","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2018). Large scale gan training for high fidelity natural image synthesis. In International conference on learning representations."},{"key":"2410_CR5","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. In International conference on learning representations."},{"key":"2410_CR6","unstructured":"Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., & Chan, W. (2021). Wavegrad: Estimating gradients for waveform generation. In: International Conference on Learning Representations"},{"key":"2410_CR7","unstructured":"De Bortoli, V., Thornton, J., Heng, J., & Doucet, A. (2021). Diffusion schr\u00f6dinger bridge with applications to score-based generative modeling. In Advances in neural information processing systems."},{"key":"2410_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2410_CR9","unstructured":"Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. In Advances in neural information processing systems."},{"key":"2410_CR10","unstructured":"Dockhorn, T., Vahdat, A., & Kreis, K. (2022). Score-based generative modeling with critically-damped Langevin diffusion. In International conference on learning representations."},{"key":"2410_CR11","doi-asserted-by":"crossref","unstructured":"Friston, K. (2010). The free-energy principle: a unified brain theory? Nature Reviews Neuroscience 11(2).","DOI":"10.1038\/nrn2787"},{"key":"2410_CR12","unstructured":"Gardiner, C. W., et al. (1985). Handbook of stochastic methods."},{"key":"2410_CR13","doi-asserted-by":"crossref","unstructured":"Girolami, M., & Calderhead, B. (2011). Riemann manifold Langevin and Hamiltonian Monte Carlo methods. Journal of the Royal Statistical Society: Series B (Statistical Methodology).","DOI":"10.1111\/j.1467-9868.2010.00765.x"},{"key":"2410_CR14","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems."},{"key":"2410_CR15","doi-asserted-by":"crossref","unstructured":"Haussmann, U. G., & Pardoux, E. (1986). Time reversal of diffusions. The Annals of Probability.","DOI":"10.1214\/aop\/1176992362"},{"key":"2410_CR16","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020) Denoising diffusion probabilistic models. In Advances in neural information processing systems."},{"key":"2410_CR17","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., & Salimans, T. (2021). Cascaded diffusion models for high fidelity image generation. arXiv preprint"},{"key":"2410_CR18","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., & Fleet, D. J. (2022). Video diffusion models. arXiv preprint arXiv:2204.03458."},{"key":"2410_CR19","doi-asserted-by":"crossref","unstructured":"Hwang, C.-R., Hwang-Ma, S.-Y., & Sheu, S.-J. (2005). Accelerating diffusions. The Annals of Applied Probability.","DOI":"10.1214\/105051605000000025"},{"key":"2410_CR20","unstructured":"Hyv\u00e4rinen, A., & Dayan, P. (2005). Estimation of non-normalized statistical models by score matching. Journal of Machine Learning Research."},{"key":"2410_CR21","doi-asserted-by":"crossref","unstructured":"Jing, B., Corso, G., Berlinghieri, R., & Jaakkola, T. (2022). Subspace diffusion generative models. arXiv preprint.","DOI":"10.1007\/978-3-031-20050-2_17"},{"key":"2410_CR22","unstructured":"Jolicoeur-Martineau, A., Li, K., Pich\u00e9-Taillefer, R., Kachman, T., & Mitliagkas, I. (2021). Gotta go fast when generating data with score-based models. arXiv preprint."},{"key":"2410_CR23","unstructured":"Kang, M., Shim, W., Cho, M., & Park, J. (2021). Rebooting acgan: Auxiliary classifier gans with stable training. Advances in Neural Information Processing Systems 34."},{"key":"2410_CR24","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of gans for improved quality, stability, and variation. In International conference on learning representations."},{"key":"2410_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2410_CR26","unstructured":"Kawar, B., Elad, M., Ermon, S., & Song, J. (2022). Denoising diffusion restoration models. arXiv preprint."},{"key":"2410_CR27","unstructured":"Kim, D., Na, B., Kwon, S. J., Lee, D., Kang, W., & Moon, I.-C. (2022). Maximum likelihood training of implicit nonlinear diffusion models. arXiv preprint."},{"key":"2410_CR28","unstructured":"Kingma, D., Salimans, T., Poole, B., & Ho, J. (2021) Variational diffusion models. In Advances in neural information processing systems."},{"key":"2410_CR29","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., & Catanzaro, B. (2021). Diffwave: A versatile diffusion model for audio synthesis. In International conference on learning representations."},{"key":"2410_CR30","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images."},{"key":"2410_CR31","doi-asserted-by":"crossref","unstructured":"Lelievre, T., Nier, F., & Pavliotis, G. A. (2013). Optimal non-reversible linear drift for the convergence to equilibrium of a diffusion. Journal of Statistical Physics.","DOI":"10.1007\/s10955-013-0769-x"},{"key":"2410_CR32","doi-asserted-by":"crossref","unstructured":"Li, C., Chen, C., Carlson, D., & Carin, L. (2016) Preconditioned stochastic gradient Langevin dynamics for deep neural networks. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10200"},{"key":"2410_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision. Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2410_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) Deep learning face attributes in the wild. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.425"},{"key":"2410_CR35","unstructured":"Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2021). Pseudo numerical methods for diffusion models on manifolds. In International Conference on Learning Representations."},{"key":"2410_CR36","unstructured":"Lu, C., Zheng, K., Bao, F., Chen, J., Li, C., & Zhu, J. (2022). Maximum likelihood training for score-based diffusion odes by high order denoising score matching. In International conference on machine learning."},{"key":"2410_CR37","doi-asserted-by":"crossref","unstructured":"Ma, H., Zhang, L., Zhu, X., & Feng, J. (2022). Accelerating score-based generative models with preconditioned diffusion sampling. In European conference on computer vision.","DOI":"10.1007\/978-3-031-20050-2_1"},{"key":"2410_CR38","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., & Ermon, S. (2021). Sdedit: Guided image synthesis and editing with stochastic differential equations. In International conference on learning representations."},{"key":"2410_CR39","doi-asserted-by":"crossref","unstructured":"Meng, C., Rombach, R., Gao, R., Kingma, D., Ermon, S., Ho, J., & Salimans, T. (2023). On distillation of guided diffusion models. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"2410_CR40","doi-asserted-by":"crossref","unstructured":"Neal, R. M., et al. (2011). Mcmc using Hamiltonian dynamics. Handbook of Markov chain Monte Carlo.","DOI":"10.1201\/b10905-6"},{"key":"2410_CR41","unstructured":"Nichol, A. Q., & Dhariwal, P. (2021) Improved denoising diffusion probabilistic models. In International conference on machine learning."},{"key":"2410_CR42","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint."},{"key":"2410_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/b98874","volume-title":"Numerical optimization","author":"J Nocedal","year":"1999","unstructured":"Nocedal, J., & Wright, S. J. (1999). Numerical optimization. Springer."},{"key":"2410_CR44","doi-asserted-by":"crossref","unstructured":"Ottobre, M. (2016). Markov chain Monte Carlo and irreversibility. Reports on Mathematical Physics.","DOI":"10.1016\/S0034-4877(16)30031-3"},{"key":"2410_CR45","doi-asserted-by":"crossref","unstructured":"Rey-Bellet, L., & Spiliopoulos, K. (2015). Irreversible Langevin samplers and variance reduction: A large deviations approach. Nonlinearity.","DOI":"10.1088\/0951-7715\/28\/7\/2081"},{"key":"2410_CR46","doi-asserted-by":"crossref","unstructured":"Risken, H., & Eberly, J. (1996). The Fokker\u2013Planck equation, methods of solution and applications.","DOI":"10.1007\/978-3-642-61544-3"},{"key":"2410_CR47","unstructured":"Roberts, G.O., & Stramer, O. (2002) Langevin diffusions and metropolis-hastings algorithms. Methodology and Computing in Applied Probability."},{"key":"2410_CR48","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2410_CR49","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C. A., Ho, J., Salimans, T., Fleet, D. J., & Norouzi, M. (2021). Palette: Image-to-image diffusion models. arXiv preprint.","DOI":"10.1145\/3528233.3530757"},{"key":"2410_CR50","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint.","DOI":"10.1145\/3528233.3530757"},{"key":"2410_CR51","doi-asserted-by":"crossref","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2021). Image super-resolution via iterative refinement. arXiv preprint.","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"2410_CR52","unstructured":"Salimans, T., & Ho, J. (2022). Progressive distillation for fast sampling of diffusion models. arXiv preprint."},{"key":"2410_CR53","unstructured":"Schaaf, A., & Hateren, J. H. (1996). Modelling the power spectra of natural images: Statistics and information. Vision Research."},{"key":"2410_CR54","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning."},{"key":"2410_CR55","unstructured":"Song, Y., & Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution. In Advances in neural information processing systems."},{"key":"2410_CR56","unstructured":"Song, Y., & Ermon, S. (2020) Improved techniques for training score-based generative models. In Advances in neural information processing systems."},{"key":"2410_CR57","unstructured":"Song, Y., Dhariwal, P., Chen, M., & Sutskever, I. (2023). Consistency models."},{"key":"2410_CR58","unstructured":"Song, Y., Durkan, C., Murray, I., & Ermon, S. (2021). Maximum likelihood training of score-based diffusion models. In Advances in neural information processing systems."},{"key":"2410_CR59","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. In International conference on learning representations."},{"key":"2410_CR60","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations. In International conference on learning representations."},{"key":"2410_CR61","unstructured":"Vahdat, A., Kreis, K., & Kautz, J. (2021). Score-based generative modeling in latent space. In Advances in neural information processing systems."},{"key":"2410_CR62","doi-asserted-by":"crossref","unstructured":"Vincent, P. (2011). A connection between score matching and denoising autoencoders. Neural Computation 23(7).","DOI":"10.1162\/NECO_a_00142"},{"key":"2410_CR63","unstructured":"Welling, M., & Teh, Y. W. (2011). Bayesian learning via stochastic gradient Langevin dynamics. In International conference on machine learning."},{"key":"2410_CR64","first-page":"67","volume":"35","author":"S Wright","year":"1999","unstructured":"Wright, S., Nocedal, J., et al. (1999). Numerical optimization. Science, 35, 67\u201368.","journal-title":"Science"},{"key":"2410_CR65","unstructured":"Xiao, Z., Kreis, K., & Vahdat, A. (2022). Tackling the generative learning trilemma with denoising diffusion gans. In International conference on learning representations."},{"key":"2410_CR66","unstructured":"Yang, L., Huang, Z., Song, Y., Hong, S., Li, G., Zhang, W., Cui, B., Ghanem, B., & Yang, M.-H. (2022). Diffusion-based scene graph to image generation with masked contrastive pre-training. arXiv preprint."},{"key":"2410_CR67","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., & Yang, M.-H. (2023). Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys 56(4).","DOI":"10.1145\/3626235"},{"key":"2410_CR68","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015). Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint."},{"key":"2410_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., & Wu, J. (2021). 3d shape generation and completion through point-voxel diffusion. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV48922.2021.00577"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02410-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02410-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02410-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:59:52Z","timestamp":1749275992000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02410-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,21]]},"references-count":69,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["2410"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02410-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2025,3,21]]},"assertion":[{"value":"13 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}