2025-08-29
PtyGenography: Using generative models for regularization of the phase retrieval problem
Publication
Publication
Presented at the
International Conference on Sampling Theory and Applications (SampTA) (July 2025), Vienna, Austria
In phase retrieval and similar inverse problems, the stability of solutions across different noise levels is crucial for applications. One approach to promote it is using signal priors in a form of a generative model as a regularization, at the expense of introducing a bias in the reconstruction. In this paper, we explore and compare the reconstruction properties of classical and generative inverse problem formulations. We propose a new unified reconstruction approach that mitigates overfitting to the generative model for varying noise levels.
| Additional Metadata | |
|---|---|
| , , , , , , | |
| doi.org/10.1109/SampTA64769.2025.11133569 | |
| International Conference on Sampling Theory and Applications (SampTA) | |
| Organisation | Computational Imaging |
|
Aslan, S., van Leeuwen, T., Mosk, A., & Salanevich, P. (2025). PtyGenography: Using generative models for regularization of the phase retrieval problem. In International Conference on Sampling Theory and Applications (SampTA) (pp. 1–5). doi:10.1109/SampTA64769.2025.11133569 |
|
