Multimode Optical Fiber Transmission with a Deep Learning Network

TL;DR

This paper demonstrates that a deep convolutional neural network can accurately learn and invert the complex input-output relationships of a multimode optical fiber, enabling high-fidelity image transmission and transfer learning.

Contribution

It introduces a deep learning approach to model and invert multimode fiber transmission, achieving high accuracy and transferability without explicit physical modeling.

Findings

Achieved ~98% image fidelity compared to traditional methods.

Successfully trained the network for transfer learning across different image classes.

Demonstrated non-linear inversion of speckle patterns in multimode fibers.

Abstract

Multimode fibers (MMF) are an example of a highly scattering medium which scramble the coherent light propagating within them and produce seemingly random patterns. Thus, for applications such as imaging and image projection through a MMF, careful measurements of the relationship between inputs and outputs of the fiber are required. We show, as a proof of concept, that a deep learning neural network can learn the input-output relationship in a 0.75 m long MMF. Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the non-linear relationships between the amplitude of the speckle pattern obtained at the output of the fiber and the phase or amplitude at the input of the fiber. Effectively the network performs a non-linear inversion task. We obtained image fidelity (correlation) of ~98% compared with the image obtained using the measured matrix of the system. We further show that the network can be trained for transfer learning, i.e. it can transmit images through the MMF which belongs to another class which were not used for training/testing.