Deep Hybrid Scattering Image Learning

TL;DR

This paper introduces a deep neural network based on U-net that can simultaneously restore images distorted by different scattering media, demonstrating strong reconstruction capabilities and generalization in optical transmission applications.

Contribution

The work presents a novel deep learning approach capable of restoring images affected by multiple scattering media using a blended training dataset, expanding machine learning's role in optics.

Findings

Effective reconstruction of images distorted by glass diffusers and multi-mode fibers

Good generalization to images outside the training dataset

Demonstrates potential for optical transmission studies

Abstract

A well-trained deep neural network is shown to gain capability of simultaneously restoring two kinds of images, which are completely destroyed by two distinct scattering medias respectively. The network, based on the U-net architecture, can be trained by blended dataset of speckles-reference images pairs. We experimentally demonstrate the power of the network in reconstructing images which are strongly diffused by glass diffuser or multi-mode fiber. The learning model further shows good generalization ability to reconstruct images that are distinguished from the training dataset. Our work facilitates the study of optical transmission and expands machine learning's application in optics.