Deep Phase Retrieval by a Learnable Filtered Spectral Initialization

David Morales,Andres Jerez,Henry Arguello

OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP)（2021）

Cited 0|Views1

No score

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.

Translated text

Key words

learnable filtered spectral initialization,phase,retrieval

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined