Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network

Abstract

Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep learning approach can make high-quality and highly generalizable predictions through unseen diffusers. Here, we propose a new deep neural network (DNN) model that is agnostic to a broader class of perturbations including scatterer change, displacements, and system defocus up to 10X depth of field. In addition, we develop a new analysis framework for interpreting the mechanism of our DNN model and visualizing its generalizability based on an unsupervised dimension reduction technique. We show that our DNN can unmix the scattering-specific information and extract the object-specific information so as to achieve generalization under different scattering conditions. Our work paves the way to a highly robust and interpretable deep learning approach to imaging through scattering media.

References in corpus (11)

• Measuring the Transmission Matrix in Optics : An Approach to the Study and Control of Light Propagation in Disordered Media
• Non-invasive real-time imaging through scattering layers and around corners via speckle correlations
• Image Transmission Through an Opaque Material
• Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
• Learning to see through multimode fibers
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Characterization of the angular memory effect of scattered light in biological tissues
• Light scattering control in transmission and reflection with neural networks
• Single-shot non-invasive three-dimensional imaging through scattering media
• On the interplay between physical and content priors in deep learning for computational imaging

Cited by in corpus (5)

• Roadmap on Wavefront Shaping and deep imaging in complex media
• Image transmission through a flexible multimode fiber by deep learning
• Adaptive 3D descattering with a dynamic synthesis network
• Learning Diffractive Optical Communication Around Arbitrary Opaque Occlusions
• Model-free estimation of the Cramér-Rao bound for deep-learning microscopy in complex media