Hybrid Coding and Weakly-Supervised Approach for Depth Estimation from Wrapped Phase

Abstract

Fringe projection profilometry (FPP) is one of the widely used techniques for 3D surface imaging. Deep learning (DL)-based fringe-to-depth reconstruction methods have aroused extensive research interest. This paper presents a hybrid coding pattern to improve depth-reconstruction accuracy. The hybrid coding wrapped phase is used to replace the fringe image as the input to neural networks. This replacement improves the accuracy of the reconstruction and facilitates the transfer from simulated to real scenarios. A weakly supervised framework and a novel loss function are proposed for fine-tuning the pre-trained model using real data without labels. The proposed approach is evaluated on the largest real-scene dataset to date, which includes 9,000 samples. Experiments demonstrate that this method outperforms the three supervised methods and achieves depth accuracy in terms of a mean absolute error (MAE) of 0.264 mm within a depth range of 120 mm. The dataset and source code is available at https://github.com/K-Jie/Hybrid_wrapped_phase_to_depth.