Saved in:
Bibliographic Details
Main Authors: Azimi, Rambod, Grinberg, Yuri, Xu, Dan-Xia, Liboiron-Ladouceur, Odile
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.11505
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915856570646528
author Azimi, Rambod
Grinberg, Yuri
Xu, Dan-Xia
Liboiron-Ladouceur, Odile
author_facet Azimi, Rambod
Grinberg, Yuri
Xu, Dan-Xia
Liboiron-Ladouceur, Odile
contents Silicon photonic devices often exhibit fabrication-induced variations such as over-etching, underetching, and corner rounding, which can significantly alter device performance. These variations are non-uniform and are influenced by feature size and shape. Accurate digital twins are therefore needed to predict the range of possible fabricated outcomes for a given design. In this paper, we introduce Gen-Fab, a conditional generative adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes. The proposed method takes a design layout (in GDS format) as input and produces diverse high-resolution predictions similar to scanning electron microscope (SEM) images of fabricated devices, capturing the range of process variations at the nanometer scale. To enable one-to-many mapping, we inject a latent noise vector at the model bottleneck. We compare Gen-Fab against three baselines: (1) a deterministic U-Net predictor, (2) an inference-time Monte Carlo Dropout U-Net, and (3) an ensemble of varied U-Nets. Evaluations on an out-of-distribution dataset of fabricated photonic test structures demonstrate that Gen-Fab outperforms all baselines in both accuracy and uncertainty modeling. An additional distribution shift analysis further confirms its strong generalization to unseen fabrication geometries. Gen-Fab achieves the highest intersection-over-union (IoU) score of 89.8%, outperforming the deterministic U-Net (85.3%), the MC-Dropout U-Net (83.4%), and varying U-Nets (85.8%). It also better aligns with the distribution of real fabrication outcomes, achieving lower Kullback-Leibler divergence and Wasserstein distance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11505
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices
Azimi, Rambod
Grinberg, Yuri
Xu, Dan-Xia
Liboiron-Ladouceur, Odile
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Silicon photonic devices often exhibit fabrication-induced variations such as over-etching, underetching, and corner rounding, which can significantly alter device performance. These variations are non-uniform and are influenced by feature size and shape. Accurate digital twins are therefore needed to predict the range of possible fabricated outcomes for a given design. In this paper, we introduce Gen-Fab, a conditional generative adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes. The proposed method takes a design layout (in GDS format) as input and produces diverse high-resolution predictions similar to scanning electron microscope (SEM) images of fabricated devices, capturing the range of process variations at the nanometer scale. To enable one-to-many mapping, we inject a latent noise vector at the model bottleneck. We compare Gen-Fab against three baselines: (1) a deterministic U-Net predictor, (2) an inference-time Monte Carlo Dropout U-Net, and (3) an ensemble of varied U-Nets. Evaluations on an out-of-distribution dataset of fabricated photonic test structures demonstrate that Gen-Fab outperforms all baselines in both accuracy and uncertainty modeling. An additional distribution shift analysis further confirms its strong generalization to unseen fabrication geometries. Gen-Fab achieves the highest intersection-over-union (IoU) score of 89.8%, outperforming the deterministic U-Net (85.3%), the MC-Dropout U-Net (83.4%), and varying U-Nets (85.8%). It also better aligns with the distribution of real fabrication outcomes, achieving lower Kullback-Leibler divergence and Wasserstein distance.
title Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.11505