# PtyGenography: using generative models for regularization of the phase retrieval problem

arXiv: https://arxiv.org/abs/2502.01338 · HTML: https://mlsanity.com/paper/2502.01338/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Phase Retrieval Under a Generative Prior](https://mlsanity.com/paper/1807.04261/) (2018)
- [Phase recovery and holographic image reconstruction using deep learning in neural networks](https://mlsanity.com/paper/1705.04286/) (2017)
- [Lensless computational imaging through deep learning](https://mlsanity.com/paper/1702.08516/) (2017)
- [Learning to Synthesize: Robust Phase Retrieval at Low Photon counts](https://mlsanity.com/paper/1907.11713/) (2019)
- [Sparse Phase Retrieval: Uniqueness Guarantees and Recovery Algorithms](https://mlsanity.com/paper/1311.2745/) (2013)
- [Noise-robust latent vector reconstruction in ptychography using deep generative models](https://mlsanity.com/paper/2311.07580/) (2023)
- [On Lipschitz Analysis and Lipschitz Synthesis for the Phase Retrieval Problem](https://mlsanity.com/paper/1506.02092/) (2015)
- [Phase retrieval with semi-algebraic and ReLU neural network priors](https://mlsanity.com/paper/2311.08833/) (2023)

## Abstract (arXiv)

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.