Deep Hybrid Scattering Image Learning

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.

arXiv comment8 pages, 6 figures

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• PCANet: A Simple Deep Learning Baseline for Image Classification?
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Image Transmission Through an Opaque Material
• Focusing and Compression of Ultrashort Pulses through Scattering Media
• Learning to see through multimode fibers
• Vortex knots in light
• Computational ghost imaging using deep learning
• Real-time coherent diffraction inversion using deep generative networks
• Random Projections through multiple optical scattering: Approximating kernels at the speed of light

Cited by in corpus (5)

• Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
• Learning-based real-time method to looking through scattering medium beyond the memory effect
• Characterising optical fibre transmission matrices using metasurface reflector stacks for lensless imaging without distal access
• Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
• Image reconstruction through a multimode fiber with a simple neural network architecture