Abstract
This work proposes a deep neural network approach for the phase retrieval problem, which learns a filtered spectral initialization. Simulation results show that the proposed approach requires fewer snapshots and power iterations than state-of-the-art.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Wei-Cheng Chao and Shang-Da Yang
JW1A.86 CLEO: Applications and Technology (CLEO:A&T) 2021
Kshitij Tayal, Raunak Manekar, Zhong Zhuang, David Yang, Vipin Kumar, Felix Hofmann, and Ju Sun
JW2A.37 Applied Industrial Spectroscopy (AIS) 2021
Raunak Manekar, Kshitij Tayal, Zhong Zhuang, Chieh-Hsin Lai, Vipin Kumar, and Ju Sun
CTh4A.4 Computational Optical Sensing and Imaging (COSI) 2021