Light scattering control in transmission and reflection with neural networks
arXiv:1805.05602 · doi:10.1364/OE.26.030911
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.
arXiv comment31 pages + 13 figures. Supplementary videos available in: https://www.osapublishing.org/oe/abstract.cfm?uri=oe-26-23-30911
References in corpus (22)
- Deep Learning in Neural Networks: An Overview
- Measuring the Transmission Matrix in Optics : An Approach to the Study and Control of Light Propagation in Disordered Media
- Image Transmission Through an Opaque Material
- Deep Learning Microscopy
- Deep-STORM: super-resolution single-molecule microscopy by deep learning
- Light fields in complex media: mesoscopic scattering meets wave control
- Experimental demonstration of painting arbitrary and dynamic potentials for Bose-Einstein condensates
- Learning to see through multimode fibers
- Reference-less measurement of the transmission matrix of a highly scattering material using a DMD and phase retrieval techniques
- Smart optical coherence tomography for ultra-deep imaging through highly scattering media
- Focusing Light through Random Photonic Media by Binary Amplitude Modulation
- Online learning of the transfer matrix of dynamic scattering media: wavefront shaping meets multidimensional time series
- Transmission-matrix-based point-spread-function engineering through a complex medium
- Focusing light through dynamical samples using fast closed-loop wavefront optimization
- Focusing of light energy inside a scattering medium by controlling the time-gated multiple light scattering
- Optogenetic control of cell signaling pathway through scattering skull using wavefront shaping
- Intensity correlations between reflected and transmitted speckle patterns
- Machine learning based localization and classification with atomic magnetometers
- Measuring large optical reflection matrices of turbid media
- Mutual information between reflected and transmitted speckle images
- Iterative, backscatter-analysis algorithms for increasing transmission and focusing light through highly-scattering random media
- Backscatter analysis based algorithms for increasing transmission through highly-scattering random media using phase-only modulated wavefronts
Cited by in corpus (16)
- DeepSTORM3D: dense three dimensional localization microscopy and point spread function design by deep learning
- Transmission of natural scene images through a multimode fibre
- Roadmap on Wavefront Shaping and deep imaging in complex media
- Seeing through multimode fibers with real-valued intensity transmission matrices
- Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network
- Adaptive 3D descattering with a dynamic synthesis network
- Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders
- Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
- Spatial images from temporal data
- Spatial Mode Correction of Single Photons using Machine Learning
- Neural-network-assisted in situ processing monitoring by speckle pattern observation
- Adaptive optics with reflected light and deep neural networks
- Enhanced detection techniques of Orbital Angular Momentum states in the classical and quantum regimes
- Referenceless characterisation of complex media using physics-informed neural networks
- Model-free estimation of the Cramér-Rao bound for deep-learning microscopy in complex media
- Machine Learning in Application to Automatic Noise Processing of Solar Spectrograms