Fringe projection profilometry by conducting deep learning from its digital twin
Yi Zheng, Shaodong Wang, Qing Li, Beiwen Li
Abstract
High-accuracy and high-speed three-dimensional (3D) fringe projection profilometry (FPP) has been widely applied in many fields. Recently, researchers discovered that deep learning can significantly improve fringe analysis. However, deep learning requires numerous objects to be scanned for training data. In this paper, we propose to build the digital twin of an FPP system and perform virtual scanning using computer graphics, which can significantly save cost and labor. The proposed method extracts 3D geometry directly from a single-shot fringe image, and real-world experiments have demonstrated the success of the virtually trained model. Our virtual scanning method can automatically generate 7,200 fringe images and 800 corresponding 3D scenes within 1.5 hours.