Uncategorized

Regularising Inverse Problems with Generative Machine Learning Models



  • Scherzer, O., Grasmair, M., Grossauer, H., Haltmeier, M., Lenzen, F.: Variational regularization methods for the solution of inverse problems. In: Variational Methods in Imaging (2019)

  • Ito, K., Jin, B.: Inverse Problems: Tikhonov Theory And Algorithms. Applied Mathematics, World Scientific, Singapore (2014)

    Book 

    Google Scholar
     

  • Benning, M., Burger, M.: Modern regularization methods for inverse problems. Acta Numer. 27, 1–111 (2018)

    Article 
    MathSciNet 

    Google Scholar
     

  • Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D 60, 259–268 (1992)

    Article 
    MathSciNet 

    Google Scholar
     

  • Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54, 4311–4322 (2006)

    Article 

    Google Scholar
     

  • Venkatakrishnan, S.V., Bouman, C.A., Wohlberg, B.: Plug-and-play priors for model based reconstruction. In: GlobalSIP, pp. 945–948 (2013)

  • Meinhardt, T., Moeller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: ICCV, pp. 1799–1808 (2017)

  • Romano, Y., Elad, M., Milanfar, P.: The little engine that could: regularization by denoising (red). SIAM J. Imaging Sci. 10, 1804–1844 (2017)

    Article 
    MathSciNet 

    Google Scholar
     

  • Li, H., Schwab, J., Antholzer, S., Haltmeier, M.: NETT: solving inverse problems with deep neural networks. Inverse Probl. 36, 065005 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Obmann, D., Nguyen, L., Schwab, J., Haltmeier, M.: Sparse Anett for solving inverse problems with deep learning. In: International Symposium on Biomedical Imaging Workshops, Proceedings (2020)

  • González, M., Almansa, A., Delbracio, M., Musé, P., Tan, P.: Solving inverse problems by joint posterior maximization with a VAE prior. SIAM J. Imaging Sci. 15, 822–859 (2022)

    Article 
    MathSciNet 

    Google Scholar
     

  • Lunz, S., Öktem, O., Schönlieb, C.B.: Adversarial regularizers in inverse problems. In: NeurIPS, pp. 8507–8516 (2018)

  • Arridge, S., Maass, P., Öktem, O., Schönlieb, C.B.: Solving inverse problems using data-driven models. Acta Numer 28, 1–174 (2019)

    Article 
    MathSciNet 

    Google Scholar
     

  • Bora, A., Jalal, A., Price, E., Dimakis, A.G.: Compressed sensing using generative models. In: ICML, pp. 822–841 (2017)

  • Dhar, M., Grover, A., Ermon, S.: Modeling sparse deviations for compressed sensing using generative models. In: ICML, vol. 3, pp. 1990–2005 (2018)

  • Habring, A., Holler, M.: A generative variational model for inverse problems in imaging. SIAM J. Math. Data Sci. 4, 306–335 (2022)

    Article 
    MathSciNet 

    Google Scholar
     

  • Tripathi, S., Lipton, Z.C., Nguyen, T.Q.: Correction by projection: denoising images with generative adversarial networks. ArXiv Preprint arXiv:1803.04477 (2018)

  • Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org

  • Boink, Y.E., Brune, C.: Learned SVD: solving inverse problems via hybrid autoencoding. ArXiv Preprint arXiv:1912.10840 (2019)

  • Obmann, D., Schwab, J., Haltmeier, M.: Deep synthesis regularization of inverse problems. ArXiv Preprint arXiv:2002.00155 (2020)

  • Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML, pp. 298–321 (2017)

  • Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. NeurIPS, pp. 5768–5778 (2017)

  • Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: NeurIPS, pp. 2672–2680 (2014)

  • Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)

  • Kingma, D.P., Welling, M.: An introduction to variational autoencoders. Found. Trends Mach. Learn. 12, 307–392 (2019)

    Article 

    Google Scholar
     

  • Dave, A., Vadathya, A.K., Subramanyam, R., Baburajan, R., Mitra, K.: Solving inverse computational imaging problems using deep pixel-level prior. IEEE Trans. Comput. Imaging 5, 37–51 (2018)

    Article 

    Google Scholar
     

  • Jacobsen, J.H., Smeulders, A., Oyallon, E.: i-RevNet: deep invertible networks. In: ICLR (2018)

  • Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1×1 convolutions. In: NeurIPS, pp. 10215–10224 (2018)

  • Oberlin, T., Verm, M.: Regularization via deep generative models: an analysis point of view. In: ICIP, pp. 404–408 (2021)

  • Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: NeurIPS (2020)

  • Ramzi, Z., Remy, B., Lanusse, F., Starck, J.-L., Ciuciu, P.: Denoising score-matching for uncertainty quantification in inverse problems. In: NeurIPS (2020)

  • Jalal, A., Arvinte, M., Daras, G., Price, E., Dimakis, A.G., Tamir, J.I.: Robust compressed sensing mri with deep generative priors. In: NeurIPS (2021)

  • Behrmann, J., Vicol, P., Wang, K.-C., Grosse, R., Jacobsen, J.-H.: Understanding and mitigating exploding inverses in invertible neural networks. In: AISTATS, PMLR, vol. 130, pp. 1792–1800 (2021)

  • Gu, J., Shen, Y., Zhou, B.: Image processing using multi-code GAN prior. In: CVPR, pp. 3009–3018 (2020)

  • Mosser, L., Dubrule, O., Blunt, M.J.: Stochastic seismic waveform inversion using generative adversarial networks as a geological prior. Math. Geosci. 52, 53–79 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Chandramouli, P., Gandikota, K.V., Goerlitz, A., Kolb, A., Moeller, M.: Generative models for generic light field reconstruction. In: TPAMI (2020)

  • Asim, M., Shamshad, F., Ahmed, A.: Blind image deconvolution using deep generative priors. IEEE Trans. Comput. Imaging 6, 1493–1506 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Hand, P., Leong, O., Voroninski, V.: Phase retrieval under a generative prior. In: NeurIPS, pp. 9136–9146 (2018)

  • Hand, P., Voroninski, V.: Global guarantees for enforcing deep generative priors by empirical risk. IEEE Trans. Inf. Theory 66, 401–418 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Lei, Q., Jalal, A., Dhillon, I.S., Dimakis, A.G.: Inverting deep generative models, one layer at a time. In: NeurIPS, vol. 32 (2019)

  • Daskalakis, C., Rohatgi, D., Zampetakis, M.: Constant-expansion suffices for compressed sensing with generative priors. In: NeurIPS (2020)

  • Shah, V., Hegde, C.: Solving linear inverse problems using GAN priors: an algorithm with provable guarantees. In: ICASSP, pp. 4609–4613 (2018)

  • Jagatap, G., Hegde, C.: Algorithmic guarantees for inverse imaging with untrained network priors. In: NeurIPS, vol. 32 (2019)

  • Candes, E.J., Tao, T.: Decoding by linear programming. IEEE Trans. Inf. Theory 51, 4203–4215 (2005)

    Article 
    MathSciNet 

    Google Scholar
     

  • Peng, P., Jalali, S., Yuan, X.: Auto-encoders for compressed sensing. In: NeurIPS (2019)

  • Hegde, C.: Algorithmic aspects of inverse problems using generative models. In: 56th Annual Allerton Conference on Communication, Control, and Computing, pp. 166–172 (2019)

  • Menon, S., Damian, A., Hu, S., Ravi, N., Rudin, C.: Pulse: self-supervised photo upsampling via latent space exploration of generative models. In: CVPR, pp. 2437–2445 (2020)

  • Daras, G., Dean, J., Jalal, A., Dimakis, A.G.: Intermediate layer optimization for inverse problems using deep generative models. In: ICML (2021)

  • Gunn, S., Cocola, J., Hand, P.: Regularized training of intermediate layers for generative models for inverse problems. arXiv preprint arXiv:2203.04382 (2022)

  • Narnhofer, D., Hammernik, K., Knoll, F., Pock, T.: Inverse GANs for accelerated MRI reconstruction. In: SPIE—The International Society for Optical Engineering, p. 45 (2019)

  • Hussein, S.A., Tirer, T., Giryes, R.: Image-adaptive GAN based reconstruction. In: AAAI, pp. 3121–3129 (2019)

  • White, T.: Sampling generative networks. arXiv:1609.04468 (2016)

  • Dai, B., Wipf, D.: Diagnosing and enhancing VAE models. In: ICLR (2019)

  • Bauer, M., Mnih, A.: Resampled priors for variational autoencoders. In: PMLR, pp. 66–75 (2020)

  • Veen, D.V., Jalal, A., Soltanolkotabi, M., Price, E., Vishwanath, S., Dimakis, A.G.: Compressed sensing with deep image prior and learned regularization. ArXiv Preprint (2018)

  • Yeh, R.A., Chen, C., Lim, T.Y., Schwing, A.G., Hasegawa-Johnson, M., Do, M.N.: Semantic image inpainting with deep generative models. In: CVPR, pp. 6882–6890 (2017)

  • Lahiri, A., Jain, A.K., Nadendla, D., Biswas, P.K.: Faster unsupervised semantic inpainting: a GAN based approach. In: ICIP, pp. 2706–2710 (2019)

  • Anirudh, R., Thiagarajan, J.J., Kailkhura, B., Bremer, T.: MimicGAN: robust projection onto image manifolds with corruption mimicking. In: IJCV (2020)

  • Adler, J., Öktem, O.: Deep Bayesian inversion. ArXiv Preprint (2018)

  • Park, H.S., Baek, J., You, S.K., Choi, J.K., Seo, J.K.: Unpaired image denoising using a generative adversarial network in X-ray CT. IEEE Access 7, 110414–110425 (2019)

    Article 

    Google Scholar
     

  • Yang, G., Yu, S., Dong, H., Slabaugh, G., Dragotti, P.L., Ye, X., Liu, F., Arridge, S., Keegan, J., Guo, Y., Firmin, D.: Dagan: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans. Med. Imaging 37, 1310–1321 (2018)

    Article 

    Google Scholar
     

  • Lv, J., Zhu, J., Yang, G.: Which GAN? a comparative study of generative adversarial network-based fast MRI reconstruction. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 379, 20200203 (2021)

    Article 
    MathSciNet 

    Google Scholar
     

  • Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2242–2251 (2017)

  • Oh, G., Sim, B., Chung, H.J., Sunwoo, L., Ye, J.C.: Unpaired deep learning for accelerated MRI using optimal transport driven CycleGAN. IEEE Trans. Comput. Imaging 6, 1285–1296 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Sim, B., Oh, G., Ye, J.C.: Optimal transport structure of CycleGAN for unsupervised learning for inverse problems. In: ICASSP, pp. 8644–8647 (2020)

  • Kabkab, M., Samangouei, P., Chellappa, R.: Task-aware compressed sensing with generative adversarial networks. In: AAAI, pp. 2297–2304 (2018)

  • Gupta, H., McCann, M.T., Donati, L., Unser, M.: CryoGAN: a new reconstruction paradigm for single-particle cryo-EM via deep adversarial learning. IEEE Trans. Comput. Imaging 7, 759–774 (2021)

    Article 
    MathSciNet 

    Google Scholar
     

  • Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. Int. J. Comput. Vis. 128, 1867–1888 (2020)

    Article 

    Google Scholar
     

  • Dittmer, S., Kluth, T., Maass, P., Baguer, D.O.: Regularization by architecture: a deep prior approach for inverse problems. J. Math. Imaging Vis. 62, 456–470 (2020)

    Article 
    MathSciNet 

    Google Scholar
     

  • Borji, A.: Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst. 179, 41–65 (2019)

    Article 

    Google Scholar
     

  • Theis, L., Oord, A.V.D., Bethge, M.: A note on the evaluation of generative models. In: ICLR (2016)

  • Rubner, Y., Tomasi, C., Guibas, L.J.: Metric for distributions with applications to image databases. In: ICCV, pp. 59–66 (1998)

  • Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS, pp. 6627–6638 (2017)

  • Gretton, A., Borgwardt, K.M., Rasch, M.J., Smola, A., Schölkopf, B., Gretton, A.S.: A kernel two-sample test. JMLR 13, 723–773 (2012)

    MathSciNet 

    Google Scholar
     

  • Lopez-Paz, D., Oquab, M.: Revisiting classifier two-sample tests. In: ICLR (2017)

  • Arora, S., Risteski, A., Zhang, Y.: Do GANs learn the distribution? Some theory and empirics. In: ICLR, pp. 1–16 (2018)

  • LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2323 (1998)

    Article 

    Google Scholar
     

  • Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS, pp. 2234–2242 (2016)

  • GoogleResearch: TensorFlow: large-scale machine learning on heterogeneous systems. Software available from tensorflow.org

  • Bredies, K., Lorenz, D.: Mathematical Image Processing, pp. 1–469. Springer, Berlin (2018)

    Book 

    Google Scholar
     

  • Flamary, R., Courty, N.: POT python optimal transport library. J. Mach Learn. Res. 22, 3571–3578 (2021)


    Google Scholar
     

  • Censor, Y.: The Mathematics of Computerized Tomography, vol. 18, p. 283. SIAM, New Delhi (2002)


    Google Scholar
     

  • Davenport, M.A., Duarte, M.F., Eldar, Y.C., Kutyniok, G.: Introduction to Compressed Sensing

  • Adler, J., Kohr, H., Öktem, O.: Operator Discretization Library (ODL)

  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, É.: Scikit-learn: machine learning in python. JMLR 12, 2825–2830 (2011)

    MathSciNet 

    Google Scholar
     

  • Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40, 120–145 (2011)

    Article 
    MathSciNet 

    Google Scholar
     

  • Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 459–494 (2014)

    Article 
    MathSciNet 

    Google Scholar
     

  • Tikhonov, A.N., Goncharsky, A.V., Stepanov, V.V., Yagola, A.G.: Numerical Methods for the Solution of Ill-Posed Problems. Kluwer Academic, Netherlands (1995)

    Book 

    Google Scholar
     

  • Knoll, F., Zbontar, J., Sriram, A., Muckley, M.J., Bruno, M., Defazio, A., Parente, M., Geras, K.J., Katsnelson, J., Chandarana, H., Zhang, Z., Drozdzalv, M., Romero, A., Rabbat, M., Vincent, P., Pinkerton, J., Wang, D., Yakubova, N., Owens, E., Zitnick, C.L., Recht, M.P., Sodickson, D.K., Lui, Y.W.: fastMRI: a publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning. Radiol. Artif. Intell. 2, 190007 (2020)

    Article 

    Google Scholar
     

  • Zbontar, J., Knoll, F., Sriram, A., Murrell, T., Huang, Z., Muckley, M.J., Defazio, A., Stern, R., Johnson, P., Bruno, M., Parente, M., Geras, K.J., Katsnelson, J., Chandarana, H., Zhang, Z., Drozdzal, M., Romero, A., Rabbat, M., Vincent, P., Yakubova, N., Pinkerton, J., Wang, D., Owens, E., Zitnick, C.L., Recht, M.P., Sodickson, D.K., Lui, Y.W.: fastMRI: an open dataset and benchmarks for accelerated MRI. ArXiv Preprint (2018)



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *