Complex phase modulation of liquid crystal devices with deep learning

Abstract

A deep learning-based phase modulation method for liquid crystal (LC) devices was demonstrated. For LC devices with a single-electrode structure, achieving complex phase distributions is highly challenging. Meanwhile, multi-electrode LC devices, as pixel resolution increases and electrode size decreases, encounter issues of cumbersome modulation steps and reduced modulation accuracy during the phase modulation process. This method uses the concept of field to modulate the phase of the LC device, providing an effective phase modulation scheme. By establishing a deep learning model, it maps the phase retardation distribution of LC devices onto the electric field distribution. This method effectively mitigates the phase modulation issues arising from the fringe field effect, enabling an accurate and precise phase modulation distribution.