Self-supervised phase unwrapping in fringe projection profilometry
This addresses accuracy limitations in 3D shape measurement for applications like motion blur and low reflectivity, but it is incremental as it builds on existing deep-learning methods by removing the need for labeled data.
They tackled the problem of limited measurement accuracy in fringe projection profilometry due to phase errors in dual-frequency temporal phase unwrapping, and their self-supervised method achieved higher depth accuracy by retrieving absolute fringe order from a single phase map with 64 periods.
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.