Phase Retrieval Based on DC and DnCNN

TL;DR

This paper proposes enhanced phase retrieval algorithms that incorporate difference of convex functions and DnCNN denoising, demonstrating improved noise robustness and performance through extensive experiments.

Contribution

It introduces two novel algorithms, prDeep-DC and prDeep-L2, combining DC programming and DnCNN for noise-robust phase retrieval.

Findings

Achieves excellent quantitative performance

Demonstrates superior visual quality

Shows robustness to noise in phase retrieval

Abstract

This paper investigates noise-robust phase retrieval by enhancing the prDeep architecture with difference of convex functions (DC) and DnCNN-based denoising regularization. This research introduces two novel algorithms, prDeep-DC and prDeep-L2, which demonstrably achieve excellent quantitative and visual performance, as confirmed by extensive numerical experiments.