Dr. AmirEhsan Khorashadizadeh

Kurzbeschreibung
Post Doc
Amir's profile picture
Paul Scherrer Institut PSI
Forschungsstrasse 111
5232 Villigen PSI
Schweiz

Amir is a postdoctoral fellow in the Computational X-ray Imaging group at the Paul Scherrer Institute (PSI). His research lies at the intersection of deep learning and computational imaging, with a particularfocus on developing physics-informed neural networks for psychography and tomography imaging. He collaborates with the Swiss Data Science Center (SDSC) on the CHIP project, "MaCHIne-Learning-assisted Ptychographic nanotomography".

Homepage

Biography

Amir received his PhD in Computer Science from the University of Basel in 2024. During his doctoral studies, he was awarded a prestigious grant to spend nine months as a visiting researcher at University College London (UCL), where he focused on cosmological imaging problems.

Selected publications

A full list of publications can be found in Amir's google scholar.

[1] AmirEhsan Khorashadizadeh, Tobias Liaudat, Tianlin Liu, Jason McEwen and Ivan Dokmanić.
'Scalable Local Image Reconstruction with Implicit Neural Representation.' Preprint 2024.

[2] AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu and Ivan Dokmanić.
'GLIMPSE: Generalized Local Imaging with MLPs.' Preprint 2024.

[3] AmirEhsan Khorashadizadeh, Anadi Chaman, Valentin Debarnot and Ivan Dokmanić.
'FunkNN: Neural Interpolation for Functional Generation.' International Conference on Learning Representations (ICLR 2023).

[4] AmirEhsan Khorashadizadeh, Vahid Khorashadizadeh, Sepehr Eskandari , Guy A. E. Vandenbosch and Ivan Dokmanić.
'Deep Injective Prior for Inverse Scattering.' IEEE Transactions on Antennas and Propagation 2023.

[5] AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaeiharandi, Maarten V. de Hoop and Ivan Dokmanić.  'Conditional Injective Flows for Bayesian Imaging.' IEEE Transactions on Computational Imaging 2023.

[6] Kothari, Konik, AmirEhsan Khorashadizadeh, Maarten de Hoop, and Ivan Dokmanić. 'Trumpets: Injective flows for inference and inverse problems.' Uncertainty in Artificial Intelligence (UAI 2021).