![](figures/photo1.jpg)
I am a last-year Ph.D. student at the University of Basel. I was a researcher at University College London (UCL) for 9 months in 2023. I work with Prof. Ivan Dokmanić and Prof. Jason McEwen. My research lies at the intersection of deep learning and computational imaging. I am interested in building physics-informed neural networks for solving scientific inverse problems.
News
- July 2024: I have been invited by the Signal Processing Society (SPS) to present a webinar on deep generative models for Bayesian imaging.
- May 2024: I give a talk on physics-informed neural networks for cosmological inverse problems at the Cosmo 21 Conference in Chania, Greece.
- Jan 2024: Our recent preprint is now available on ArXiv.
- Nov 2023: Our paper “Conditional Injective Flows for Bayesian Imaging” is among the top 25 most downloaded papers in IEEE Transactions on Computational Imaging (TCI) from Sept. 2022 - Sept. 2023.
- Aug 2023: Our paper “Deep Injective Prior for Inverse Scattering” has been accepted by IEEE Transactions on Antennas and Propagation.
- July 2023: I am awarded a grant by the Promotion of Young Talent at the University of Basel to spend 9 months as a visiting scholar at University College London (UCL), focused on leveraging deep generative models for astrophysics in Prof. Jason McEwen’s group.
- Feb 2023: Our paper “Conditional Injective Flows for Bayesian Imaging” has been accepted by IEEE Transactions on Computational Imaging.
- Jan 2023: Our paper “FunkNN: Neural Interpolation for Functional Generation” has been accepted by ICLR 2023.
- Dec 2022: Our paper has been accepted by European Conference on Antennas and Propagation (EUCAP 2023).
- Jun 2021: Our paper has been accepted by the Conference on Uncertainty in Artificial Intelligence (UAI 2021).
- April 2020: I started my Ph.D. at the SADA group, University of Basel.
Publications
![](figures/glimpse.png)
GLIMPSE: Generalized Local Imaging with MLPs
AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu and Ivan Dokmanić
Preprint 2024
![](https://sada.dmi.unibas.ch/gallery/preview/186/screenshot-2023-01-02-at-20-49-14@2x.png)
FunkNN: Neural Interpolation for Functional Generation
AmirEhsan Khorashadizadeh, Anadi Chaman, Valentin Debarnot and Ivan Dokmanić
ICLR 2023
![](https://sada.dmi.unibas.ch/gallery/preview/192/screenshot-2023-01-03-at-11-10-37@2x.png)
Deep Injective Prior for Inverse Scattering
AmirEhsan Khorashadizadeh, Vahid Khorashadizadeh, Sepehr Eskandari, Guy A.E. Vandenbosch and Ivan Dokmanić
IEEE Transactions on Antennas and Propagation 2023
![](https://sada.dmi.unibas.ch/gallery/preview/149/screenshot-2022-05-17-at-18-01-42@2x.png)
Conditional Injective Flows for Bayesian Imaging
AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaei Harandi, Maarten de Hoop and Ivan Dokmanić
IEEE Transactions on Computational Imaging 2023
![](https://sada.dmi.unibas.ch/gallery/preview/169/screenshot-2022-12-10-at-13-51-06@2x.png)
Deep Variational Inverse Scattering
AmirEhsan Khorashadizadeh, Ali Aghababaei, Tin Vlavsić, Hieu Nguyen and Ivan Dokmanić
European Conference on Antennas and Propagation (EuCAP) 2023
![](https://sada.dmi.unibas.ch/gallery/preview/184/screenshot-2023-01-02-at-15-53-58@2x.png)
Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering
Tin Vlašić, Hieu Nguyen, AmirEhsan Khorashadizadeh and Ivan Dokmanić
Asilomar Conference on Signals, Systems, and Computers 2022
![](https://sada.dmi.unibas.ch/gallery/preview/110/networkat2x@2x.png)
Trumpets: Injective flows for inference and inverse problems
Konik Kothari, AmirEhsan Khorashadizadeh, Maarten de Hoop and Ivan Dokmanić
UAI 2021