High-speed structured light 3D imaging and metrology empowered by deep learning (Conference Presentation)

In this talk, we introduce our recent efforts to apply deep-learning approaches to structured light 3D imaging and metrology, especially Fringe projection profilometry (FPP). We show that the deep-learning-enabled fringe analysis approach can significantly boost the accuracy and improve the quality of the phase reconstruction compared to conventional single-fringe phase retrieval approaches. Deep learning can also be used to achieve single-frame, high-precision, unambiguous 3D shape reconstruction, which is expected to fill the speed "gap" between 3D imaging and 2D sensing and enables FPP techniques to go a step further in high-speed and high-accuracy 3D surface imaging of transient events.