Light scattering control in transmission and reflection with neural networks

TL;DR

This paper presents a machine-learning approach using neural networks to control and shape light transmission and reflection through scattering media, enabling improved optical imaging and sensing.

Contribution

The study introduces neural network-based methods for wavefront correction and for relating transmitted and reflected speckle patterns, advancing light control in scattering media.

Findings

Neural networks can effectively correct wavefront distortions caused by scattering.

Reflected light can be used to infer transmission control, enabling non-invasive focusing.

The approach improves light delivery in opaque media for imaging and sensing applications.

Abstract

Scattering often limits the controlled delivery of light in applications such as biomedical imaging, optogenetics, optical trapping, and fiber-optic communication or imaging. Such scattering can be controlled by appropriately shaping the light wavefront entering the material. Here, we demonstrate a machine-learning approach for light control. Using pairs of binary intensity patterns and intensity measurements we train neural networks (NNs) to provide the wavefront corrections necessary to shape the beam after the scatterer. Additionally, we demonstrate that NNs can be used to find a functional relationship between transmitted and reflected speckle patterns. As a proof of the validity of this relationship, we demonstrate focusing and scanning of light in transmission through opaque media using reflected light. Our approach demonstrates the versatility of NNs for light shaping and for efficiently and flexibly correcting for scattering. In particular, the feasibility of transmission control based on reflected light opens up new opportunities for applications in optical imaging, sensing, and light delivery.