Phase Retrieval Using Conditional Generative Adversarial Networks
This work addresses phase retrieval for applications like imaging and signal processing, offering an incremental improvement over prior deep learning approaches.
The paper tackled phase retrieval problems by applying conditional generative adversarial networks, achieving more robust optimization and detailed results compared to existing projection-based and neural network methods, with demonstrated robustness to noise.
In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems. We show that including knowledge of the measurement process at training time leads to an optimization at test time that is more robust to initialization than existing approaches involving generative models. In addition, conditioning the generator network on the measurements enables us to achieve much more detailed results. We empirically demonstrate that these advantages provide meaningful solutions to the Fourier and the compressive phase retrieval problem and that our method outperforms well-established projection-based methods as well as existing methods that are based on neural networks. Like other deep learning methods, our approach is very robust to noise and can therefore be very useful for real-world applications.