Seeing invisible objects with intelligent optics

TL;DR

This paper introduces a new method using machine learning and diffractive optics to make transparent objects visible with regular cameras.

Contribution

The novelty is performing optical transformations directly using intelligent optics, bypassing complex digital processing.

Findings

Transparent objects can be imaged directly using conventional cameras with intelligent optics.

Machine learning and diffractive optics enable in-situ measurement without interferometry.

This approach simplifies imaging of transparent objects compared to traditional methods.

Abstract

Transparent objects are invisible to traditional cameras because they can only detect intensity fluctuations, necessitating the need for interferometry followed by computationally intensive digital image processing. Now it is shown that the necessary transformations can be performed optically by combining machine learning and diffractive optics, for a direct in-situ measurement of transparent objects with conventional cameras.

Figures