Helmholtz Imaging CONNECT

Go back Home Labs Computational Imaging at DESY

Computational Imaging at DESY (FS-CI)

Computational Imaging Group and Helmholtz Imaging at DESY, lead by Martin Burger.

Computational Imaging at DESY in Helmholtz Imaging CONNECT:

Deutsches Elektronen-Synchrotron - Hamburg

PhD student in the computational imaging group at DESY
Interested in image reconstruction, inverse problems, medical imaging

In Helmholtz Imaging CONNECT
➤Modalities: 0 ➤Applications: 0 ➤Instruments: 0 ➤Labs: 2 ➤Facilities: 0 ➤Centers: 1 ➤Solutions: 0

Expert

Samira Kabri

Deutsches Elektronen-Synchrotron - Hamburg

PhD student in Mathematics in the Computational Imaging Group at DESY, led by Martin Burger.

I am primarily interested in solving inverse problems with data-driven strategies where I focus on analyzing their stability and convergence behavior. Since these properties are …

In Helmholtz Imaging CONNECT
➤Modalities: 3 ➤Applications: 3 ➤Instruments: 0 ➤Labs: 2 ➤Facilities: 0 ➤Centers: 1 ➤Solutions: 1

Expert

Tim Roith

Deutsches Elektronen-Synchrotron - Hamburg

Hi,

I'm Tim and currently a Postdoc in the computational imaging group at DESY, led by Martin Burger. I am interested in inverse problems, mathematics of data science and machine learning for imaging applications.

In Helmholtz Imaging CONNECT
➤Modalities: 0 ➤Applications: 0 ➤Instruments: 0 ➤Labs: 2 ➤Facilities: 0 ➤Centers: 1 ➤Solutions: 2

No application found.

No modality found.

No facility found.

Center

Deutsches Elektronen-Synchrotron (DESY)

DESY is one of the world’s leading accelerator centres. Researchers use the large-scale facilities at DESY to explore the microcosm in all its variety – from the interactions of tiny elementary particles and the behaviour …

In Helmholtz Imaging CONNECT
➤Applications: 152 ➤Facilities: 4 ➤Instruments: 21 ➤Labs: 86 ➤Modalities: 237 ➤Experts: 32 ➤Solutions: 4

No instrument found.

Solution

CBX: Python and Julia packages for consensus-based interacting particle methods (CBX)

Derivative-free optimization is required, whenever gradients of objective functions are not available or too expensive to evaluate. A typical imaging application, where such a situation arises, is when employing a closed-box classification tool, like a …

In Helmholtz Imaging CONNECT
➤Applications: 0 ➤Facilities: 0 ➤Centers: 1 ➤Instruments: 0 ➤Labs: 2 ➤Modalities: 0 ➤Experts: 1

Solution

Resolution-Invariant Image Classification based on Fourier Neural Operators (FNO)

Standard neural networks for imaging tasks are tied to a certain fixed image resolution they were trained on. Neural operators were proposed in Kovachki, Nikola, et al. “Neural operator: Learning maps between function spaces with …

In Helmholtz Imaging CONNECT
➤Applications: 0 ➤Facilities: 0 ➤Centers: 1 ➤Instruments: 0 ➤Labs: 2 ➤Modalities: 0 ➤Experts: 2