English

Deep S$^3$PR: Simultaneous Source Separation and Phase Retrieval Using Deep Generative Models

Machine Learning 2020-10-15 v2 Image and Video Processing Machine Learning

Abstract

This paper introduces and solves the simultaneous source separation and phase retrieval (S3^3PR) problem. S3^3PR is an important but largely unsolved problem in a number application domains, including microscopy, wireless communication, and imaging through scattering media, where one has multiple independent coherent sources whose phase is difficult to measure. In general, S3^3PR is highly under-determined, non-convex, and difficult to solve. In this work, we demonstrate that by restricting the solutions to lie in the range of a deep generative model, we can constrain the search space sufficiently to solve S3^3PR.

Cite

@article{arxiv.2002.05856,
  title  = {Deep S$^3$PR: Simultaneous Source Separation and Phase Retrieval Using Deep Generative Models},
  author = {Christopher A. Metzler and Gordon Wetzstein},
  journal= {arXiv preprint arXiv:2002.05856},
  year   = {2020}
}
R2 v1 2026-06-23T13:41:34.707Z