Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Altekrüger, Fabian"'
Contrast enhancement by Gadolinium-based contrast agents (GBCAs) is a vital tool for tumor diagnosis in neuroradiology. Based on brain MRI scans of glioblastoma before and after Gadolinium administration, we address enhancement prediction by neural n
Externí odkaz:
http://arxiv.org/abs/2410.08894
Theoretical guarantees for the robust solution of inverse problems have important implications for applications. To achieve both guarantees and high reconstruction quality, we propose to learn a pixel-based ridge regularizer with a data-dependent and
Externí odkaz:
http://arxiv.org/abs/2406.12289
Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction
Autor:
Piening, Moritz, Altekrüger, Fabian, Hertrich, Johannes, Hagemann, Paul, Walther, Andrea, Steidl, Gabriele
The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences. Recent advances were made by using methods from machine learning, in particular deep neural networks
Externí odkaz:
http://arxiv.org/abs/2312.16611
Autor:
Hagemann, Paul, Hertrich, Johannes, Altekrüger, Fabian, Beinert, Robert, Chemseddine, Jannis, Steidl, Gabriele
We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling. This MMD, which is also known as energy distance, has several advantageous properties lik
Externí odkaz:
http://arxiv.org/abs/2310.03054
Maximum mean discrepancy (MMD) flows suffer from high computational costs in large scale computations. In this paper, we show that MMD flows with Riesz kernels $K(x,y) = - \|x-y\|^r$, $r \in (0,2)$ have exceptional properties which allow their effici
Externí odkaz:
http://arxiv.org/abs/2305.11463
Autor:
Kofler, Andreas, Altekrüger, Fabian, Ba, Fatima Antarou, Kolbitsch, Christoph, Papoutsellis, Evangelos, Schote, David, Sirotenko, Clemens, Zimmermann, Felix Frederik, Papafitsoros, Kostas
We propose a method for fast and automatic estimation of spatially dependent regularization maps for total variation-based (TV) tomography reconstruction. The estimation is based on two distinct sub-networks, with the first sub-network estimating the
Externí odkaz:
http://arxiv.org/abs/2304.08350
Publikováno v:
Transactions on Machine Learning Research (TMLR), 2023
Conditional generative models became a very powerful tool to sample from Bayesian inverse problem posteriors. It is well-known in classical Bayesian literature that posterior measures are quite robust with respect to perturbations of both the prior m
Externí odkaz:
http://arxiv.org/abs/2303.15845
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:664-690, 2023
Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely. In this paper we contribute to the understanding o
Externí odkaz:
http://arxiv.org/abs/2301.11624
Autor:
Kofler, Andreas, Altekrüger, Fabian, Ba, Fatima Antarou, Kolbitsch, Christoph, Papoutsellis, Evangelos, Schote, David, Sirotenko, Clemens, Zimmermann, Felix Frederik, Papafitsoros, Kostas
We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent developments
Externí odkaz:
http://arxiv.org/abs/2301.05888
Autor:
Altekrüger, Fabian, Denker, Alexander, Hagemann, Paul, Hertrich, Johannes, Maass, Peter, Steidl, Gabriele
Publikováno v:
Inverse Problems, Volume 39, Number 6, 2023
Learning neural networks using only few available information is an important ongoing research topic with tremendous potential for applications. In this paper, we introduce a powerful regularizer for the variational modeling of inverse problems in im
Externí odkaz:
http://arxiv.org/abs/2205.12021