Self-supervised phase unwrapping in fringe projection profilometry

TL;DR

This paper introduces a self-supervised deep learning method for phase unwrapping in fringe projection profilometry, achieving higher accuracy without labeled data and handling challenging real-world conditions.

Contribution

A novel self-supervised phase unwrapping approach for single-camera FPP that surpasses traditional methods in accuracy without requiring labeled training data.

Findings

Outperforms DF-TPU in depth accuracy.

Effective on real scenes with motion blur, low reflectivity, and phase discontinuities.

Does not require labeled data for training.

Abstract

Fast-speed and high-accuracy three-dimensional (3D) shape measurement has been the goal all along in fringe projection profilometry (FPP). The dual-frequency temporal phase unwrapping method (DF-TPU) is one of the prominent technologies to achieve this goal. However, the period number of the high-frequency pattern of existing DF-TPU approaches is usually limited by the inevitable phase errors, setting a limit to measurement accuracy. Deep-learning-based phase unwrapping methods for single-camera FPP usually require labeled data for training. In this letter, a novel self-supervised phase unwrapping method for single-camera FPP systems is proposed. The trained network can retrieve the absolute fringe order from one phase map of 64-period and overperform DF-TPU approaches in terms of depth accuracy. Experimental results demonstrate the validation of the proposed method on real scenes of motion blur, isolated objects, low reflectivity, and phase discontinuity.