Deep Neural Networks for Computational Optical Form Measurements

TL;DR

This paper demonstrates that deep neural networks can effectively solve inverse problems in computational optical form measurement, offering a data-driven approach validated through virtual experiments.

Contribution

It introduces a novel deep learning method for optical surface measurement, showcasing its potential in computational optical metrology.

Findings

Deep neural networks can accurately measure optical surfaces in simulated environments.

The approach outperforms traditional methods in inverse problem solving.

Validation with virtual data confirms the method's effectiveness.

Abstract

Deep neural networks have been successfully applied in many different fields like computational imaging, medical healthcare, signal processing, or autonomous driving. In a proof-of-principle study, we demonstrate that computational optical form measurement can also benefit from deep learning. A data-driven machine learning approach is explored to solve an inverse problem in the accurate measurement of optical surfaces. The approach is developed and tested using virtual measurements with known ground truth.