Light Propagation Prediction through Multimode Optical Fibers with a Deep Neural Network
This work addresses a domain-specific problem in optical physics and imaging, offering an incremental improvement in computational methods for fiber-based light prediction.
The authors tackled the problem of predicting light propagation through multimode optical fibers by developing a deep neural network trained on data from spatial light modulation experiments, achieving excellent performance as validated by metrics like MSE, correlation coefficient, and SSIM.
This work demonstrates a computational method for predicting the light propagation through a single multimode fiber using a deep neural network. The experiment for gathering training and testing data is performed with a digital micro-mirror device that enables the spatial light modulation. The modulated patterns on the device and the captured intensity-only images by the camera form the aligned data pairs. This sufficiently-trained deep neural network frame has very excellent performance for directly inferring the intensity-only output delivered though a multimode fiber. The model is validated by three standards: the mean squared error (MSE), the correlation coefficient (corr) and the structural similarity index (SSIM).