no code implementations • 23 Oct 2023 • Moritz Erlacher, Martin Zach
Data-driven reconstruction approaches, in particular diffusion models, recently achieved remarkable success in reconstructing these data, but typically rely on estimating the coil sensitivities in an off-line step.
1 code implementation • 19 Oct 2023 • Martin Zach, Erich Kobler, Antonin Chambolle, Thomas Pock
In this work we tackle the problem of estimating the density $ f_X $ of a random variable $ X $ by successive smoothing, such that the smoothed random variable $ Y $ fulfills the diffusion partial differential equation $ (\partial_t - \Delta_1)f_Y(\,\cdot\,, t) = 0 $ with initial condition $ f_Y(\,\cdot\,, 0) = f_X $.
no code implementations • 16 Feb 2023 • Martin Zach, Thomas Pock, Erich Kobler, Antonin Chambolle
In this work we tackle the problem of estimating the density $f_X$ of a random variable $X$ by successive smoothing, such that the smoothed random variable $Y$ fulfills $(\partial_t - \Delta_1)f_Y(\,\cdot\,, t) = 0$, $f_Y(\,\cdot\,, 0) = f_X$.
no code implementations • 25 Oct 2022 • Martin Zach, Florian Knoll, Thomas Pock
We propose a novel deep neural network based regularizer which is trained in a generative setting on reference magnitude images only.
no code implementations • 23 Mar 2022 • Martin Zach, Erich Kobler, Thomas Pock
We apply the regularizer to limited-angle and few-view CT reconstruction problems, where it outperforms traditional reconstruction algorithms by a large margin.