Open AccessUnsupervised deep learning for 3D reconstruction with dual-frequency fringe projection profilometry
Author(s) -
Sizhe Fan,
Shaoli Liu,
Xu Zhang,
Hao Huang,
Wei Liu,
Peng Jin
Publication year - 2021
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.435606
Subject(s) - computer science , artificial intelligence , convolutional neural network , ground truth , deep learning , unsupervised learning , projection (relational algebra) , noise (video) , generalization , pattern recognition (psychology) , iterative reconstruction , supervised learning , artificial neural network , computer vision , image (mathematics) , algorithm , mathematics , mathematical analysis
The fringe projection profilometry (FPP) technique has been widely applied in three-dimensional (3D) reconstruction in industry for its high speed and high accuracy. Recently, deep learning has been successfully applied in FPP to achieve high-accuracy and robust 3D reconstructions in an efficient way. However, the network training needs to generate and label numerous ground truth 3D data, which can be time-consuming and labor-intensive. In this paper, we propose to design an unsupervised convolutional neural network (CNN) model based on dual-frequency fringe images to fix the problem. The fringe reprojection model is created to transform the output height map to the corresponding fringe image to realize the unsupervised training of the CNN. Our network takes two fringe images with different frequencies and outputs the corresponding height map. Unlike most of the previous works, our proposed network avoids numerous data annotations and can be trained without ground truth 3D data for unsupervised learning. Experimental results verify that our proposed unsupervised model (1) can get competitive-accuracy reconstruction results compared with previous supervised methods, (2) has excellent anti-noise and generalization performance and (3) saves time for dataset generation and labeling (3.2 hours, one-sixth of the supervised method) and computer space for dataset storage (1.27 GB, one-tenth of the supervised method).