Light Propagation Prediction through Multimode Optical Fibers with a Deep Neural Network

TL;DR

This paper presents a deep neural network approach for accurately predicting light propagation through multimode optical fibers, using experimental data from a digital micro-mirror device and intensity measurements.

Contribution

It introduces a novel deep learning method trained on experimental data to predict light transmission in multimode fibers with high accuracy.

Findings

High prediction accuracy demonstrated by MSE, correlation coefficient, and SSIM metrics.

Effective use of digital micro-mirror device for data collection.

Deep neural network outperforms traditional modeling methods.

Abstract

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).