One-step robust deep learning phase unwrapping

TLDR

Phase unwrapping remains a challenging problem in phase measurement, especially under heavy noise and aliasing, despite decades of research. The study proposes a database generation method for phase‑type objects and a one‑step deep learning phase unwrapping approach. The authors generate synthetic phase‑type object databases and train a single deep neural network to perform phase unwrapping in one step. The trained network successfully unwraps unseen phase fields of living mouse osteoblasts and dynamic candle flames, achieving superior anti‑noise and anti‑aliasing performance compared to classical methods.

Abstract

Phase unwrapping is an important but challenging issue in phase measurement. Even with the research efforts of a few decades, unfortunately, the problem remains not well solved, especially when heavy noise and aliasing (undersampling) are present. We propose a database generation method for phase-type objects and a one-step deep learning phase unwrapping method. With a trained deep neural network, the unseen phase fields of living mouse osteoblasts and dynamic candle flame are successfully unwrapped, demonstrating that the complicated nonlinear phase unwrapping task can be directly fulfilled in one step by a single deep neural network. Excellent anti-noise and anti-aliasing performances outperforming classical methods are highlighted in this paper.