About me

I am a post doctoral research associate at University College London within the Maths4DL project. I completed my PhD at the University of Bremen supervised by Peter Maass. During my PhD, I worked on the application of generative models to inverse problems in imaging. My research interest include generative modeling, in particular normalising flows and diffusion models, image reconstruction and machine learning.

Publications

2025

Denker A, Padhy S, Vargas F, Hertrich J Iterative Importance Fine-tuning of Diffusion Models, preprint.

Barbano R, Denker A, Chung H, Roh T, Arridge S, Maass P, Jin B, Ye J Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction. IEEE Transactions on Medical Imaging.

2024

Denker A, Hertrich J, Kereta Z, Cipiccia S, Erin E, Arridge S Plug-and-Play Half-Quadratic Splitting for Ptychography, preprint.

Denker A, Vargas F, Padhy S, Didi K, Mathis S, Dutordoir V, Barbano R, Mathieu E, Komorowska U, Lio P DEFT: Efficient Finetuning of Conditional Diffusion Models by Learning the Generalised h-transform. Accepted at Neurips 2024.

Denker A, Kereta Z, Singh I, Freudenberg T, Kluth T, Maass P, Arridge S Data-driven approaches for electrical impedance tomography image segmentation from partial boundary data. Applied Mathematics for Modern Challenges, 2024, 2(2): 119-139. doi: 10.3934/ammc.2024005

Denker A, Behrmann J, Boskamp T Improved Mass Calibration in MALDI MSI Using Neural Network-Based Recalibration. Analytical Chemistry 96.19 (2024): 7542-7549.

Fernsel P, Kereta Z, Denker A Convergence Properties of Score-Based Models using Graduated Optimisation for Linear Inverse Problems. IEEE MLSP 2024.

Singh I, Denker A, Barbano R, Zeljko K, Jin B, Thielemans K, Maass P, Arridge S Score-Based Generative Models for PET Image Reconstruction. Machine Learning for Biomedical Imaging (MELBA)

2023

Arndt C, Denker A, Dittmer S, Leuschner J, Nickel J, Schmidt M Model-based deep learning approaches to the Helsinki Tomography Challenge 2022. Applied Mathematics for Modern Challenges 1.2 (2023): 87-104.

Arndt C, Denker A, Dittmer S, Heilenkötter N, Iske M, Kluth T, Maass P, Nickel J Invertible residual networks in the context of regularization theory for linear inverse problems. Inverse Problems 39.12 (2023): 125018.

Arndt C, Denker A, Nickel J, Leuschner J, Schmidt M, Rigaud G In Focus-hybrid deep learning approaches to the HDC2021 challenge. Inverse Problems & Imaging 17.5 (2023).

Altekrueger F, Denker A, Hagemann P, Hertrich J, Maass P, Steidl G PatchNR: learning from very few images by patch normalizing flow regularization. Inverse Problems 39.6 (2023): 064006.

2022

Barbano R, Leuschner J, Schmidt M, Denker A, Hauptmann A, Maass P, Jin B An educated warm start for deep image prior-based micro CT reconstruction. IEEE Transactions on Computational Imaging 8 (2022): 1210-1222.

2021

Denker A, Schmidt M, Leuschner J, Maass P. Conditional Invertible Neural Networks for Medical Imaging. Journal of Imaging. 2021; 7(11):243. https://doi.org/10.3390/jimaging7110243

Leuschner J, Schmidt M, Ganguly PS, Andriiashen V, Coban SB, Denker A, Bauer D, Hadjifaradji A, Batenburg KJ, Maass P, van Eijnatten M. Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications. Journal of Imaging. 2021; 7(3):44. https://doi.org/10.3390/jimaging7030044

2020

Denker A, Schmidt M, Leuschner J, Maass P, Behrmann J. Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction. ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 18.07-18.07.2020, Wien, Österreich. online: https://invertibleworkshop.github.io/accepted_papers/index.html