Learning-based real-time method to looking through scattering medium beyond the memory effect

TL;DR

This paper introduces PDSNet, a convolutional neural network that enables real-time imaging through strong scattering media, overcoming the limited field-of-view imposed by the optical memory effect, with broad applicability to complex objects.

Contribution

The paper presents a novel neural network approach that surpasses the optical memory effect's FOV limitations for real-time imaging through scattering media.

Findings

PDSNet accurately reconstructs scattered patterns in real-time.

The method is effective across various scattering media and object scales.

It significantly extends the practical imaging capabilities through scattering media.

Abstract

Strong scattering medium brings great difficulties to optical imaging, which is also a problem in medical imaging and many other fields. Optical memory effect makes it possible to image through strong random scattering medium. However, this method also has the limitation of limited angle field-of-view (FOV), which prevents it from being applied in practice. In this paper, a kind of practical convolutional neural network called PDSNet is proposed, which effectively breaks through the limitation of optical memory effect on FOV. Experiments is conducted to prove that the scattered pattern can be reconstructed accurately in real-time by PDSNet, and it is widely applicable to retrieve complex objects of random scales and different scattering media.