Modeling Inverse Ellipsometry Problem via Flow Matching with a Large-Scale Dataset

TL;DR

This paper introduces a large-scale dataset and a novel flow matching method to improve the accuracy and robustness of inverse ellipsometry, addressing its inherent ambiguity and limitations of previous approaches.

Contribution

The paper presents EllipBench, a large-scale dataset for inverse ellipsometry, and proposes DCFM, a physics-informed flow matching framework that better captures the problem's ambiguity.

Findings

Existing methods struggle with inverse ellipsometry ambiguity.

DCFM outperforms traditional models in accuracy and robustness.

Large-scale dataset enables comprehensive evaluation of approaches.

Abstract

Inverse ellipsometry, i.e., reconstructing optical constants and film thickness from the measured phase difference $\Delta$ and amplitude ratio $\Psi$, is a fundamentally ill-posed problem. Traditional solutions rely on slow, expert-driven iterative fitting, while the development of machine learning approaches has been severely limited by the lack of large-scale, physically consistent datasets. To address this gap, we introduce \textbf{EllipBench}, a comprehensive benchmark comprising over 8 million high-precision samples spanning 98 thin-film materials and 5 substrates. Building upon this benchmark, we conduct a systematic evaluation of a broad spectrum of methods, including traditional machine learning models, deep neural networks, and Physics-Informed Neural Networks, and show that existing paradigms consistently struggle to fully resolve the inverse ellipsometry task. To better capture its inherent ambiguity, we further propose a novel \textbf{Decoupled Conditional Flow Matching (DCFM)} framework. Rather than formulating the problem as deterministic point-to-point regression, DCFM explicitly decouples geometric film thickness and incorporates it as a robust physical condition to guide a continuous vector field for modeling the inverse probability distribution of wavelength-dependent optical constants. Combined with a gradient detachment strategy and physics-based constraints, our joint architecture effectively mitigates intrinsic physical ambiguities and delivers a robust and accurate solution for inverse ellipsometry.