Saved in:
Bibliographic Details
Main Authors: Grand, Mathys Le, Urard, Pascal, Rideau, Denis, Trémas, Loumi, Maitre, Damien, Fernandez-Mouron, Louis-Henri, Fuchs, Adam, Orobtchouk, Régis
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15210
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914282843668480
author Grand, Mathys Le
Urard, Pascal
Rideau, Denis
Trémas, Loumi
Maitre, Damien
Fernandez-Mouron, Louis-Henri
Fuchs, Adam
Orobtchouk, Régis
author_facet Grand, Mathys Le
Urard, Pascal
Rideau, Denis
Trémas, Loumi
Maitre, Damien
Fernandez-Mouron, Louis-Henri
Fuchs, Adam
Orobtchouk, Régis
contents The inverse design of metasurfaces faces inherent challenges due to the nonlinear and highly complex relationship between geometric configurations and their electromagnetic behavior. Traditional optimization approaches often suffer from excessive computational demands and a tendency to converge to suboptimal solutions. This study presents a diffusion-based generative framework that incorporates a dedicated consistency constraint and advanced posterior sampling methods to ensure adherence to desired electromagnetic specifications. Through rigorous validation on small-scale metasurface configurations, the proposed approach demonstrates marked enhancements in both accuracy and reliability of the generated designs. Furthermore, we introduce a scalable methodology that extends inverse design capabilities to large-scale metasurfaces, validated for configurations of up to $98 \times 98$ nanopillars. Notably, this approach enables rapid design generation completed in minute by leveraging models trained on substantially smaller arrays ($23 \times 23$). These innovations establish a robust and efficient framework for high-precision metasurface inverse design.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15210
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhanced posterior sampling via diffusion models for efficient metasurfaces inverse design
Grand, Mathys Le
Urard, Pascal
Rideau, Denis
Trémas, Loumi
Maitre, Damien
Fernandez-Mouron, Louis-Henri
Fuchs, Adam
Orobtchouk, Régis
Optics
Mathematical Physics
The inverse design of metasurfaces faces inherent challenges due to the nonlinear and highly complex relationship between geometric configurations and their electromagnetic behavior. Traditional optimization approaches often suffer from excessive computational demands and a tendency to converge to suboptimal solutions. This study presents a diffusion-based generative framework that incorporates a dedicated consistency constraint and advanced posterior sampling methods to ensure adherence to desired electromagnetic specifications. Through rigorous validation on small-scale metasurface configurations, the proposed approach demonstrates marked enhancements in both accuracy and reliability of the generated designs. Furthermore, we introduce a scalable methodology that extends inverse design capabilities to large-scale metasurfaces, validated for configurations of up to $98 \times 98$ nanopillars. Notably, this approach enables rapid design generation completed in minute by leveraging models trained on substantially smaller arrays ($23 \times 23$). These innovations establish a robust and efficient framework for high-precision metasurface inverse design.
title Enhanced posterior sampling via diffusion models for efficient metasurfaces inverse design
topic Optics
Mathematical Physics
url https://arxiv.org/abs/2601.15210