Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices

• URL: http://arxiv.org/abs/2603.11505v1
• Date: Thu, 12 Mar 2026 03:47:40 GMT
• Title: Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices
• Abstract summary: We introduce Gen-Fab, a conditional generative adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes.<n>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.<n>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%
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction [0.26856688022781555]
  We introduce Dual-r, which generalizes multistep samplers through learnable parameters.<n>It retains the standard predictor-corrector structure while preserving second-order local accuracy.<n>It improves FID and CLIP scores in the low-NFE regime across backbones.
  arXiv  Detail & Related papers  (2026-03-04T12:14:52Z)
• Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models [77.55829017952728]
  EntPruner is an entropy-guided automatic progressive pruning framework for diffusion and flow models.<n>Experiments on DiT and SiT models demonstrate the effectiveness of EntPruner, achieving up to 2.22$times$ inference speedup.
  arXiv  Detail & Related papers  (2025-11-26T07:20:48Z)
• Generative Modeling with Bayesian Sample Inference [50.07758840675341]
  We derive a novel generative model from iterative Gaussian posterior inference.<n>Our model uses a sequence of prediction and posterior update steps to iteratively narrow down the unknown sample.<n>In experiments, we demonstrate that our model improves sample quality on ImageNet32 over both BFNs and the closely related Variational Diffusion Models.
  arXiv  Detail & Related papers  (2025-02-11T14:27:10Z)
• SEMU-Net: A Segmentation-based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images [4.875868958100446]
  We introduce SEMU-Net, a set of methods that automatically segments scanning electron microscope images (SEM) and uses them to train two deep neural network models based on U-Net and its variants. The predictor model anticipates fabrication-induced variations, while the corrector model adjusts the design to address these issues. Experimental results show that the segmentation U-Net reaches an average IoU score of 99.30%, while the corrector attention U-Net in a tandem architecture achieves an average IoU score of 98.67%.
  arXiv  Detail & Related papers  (2024-11-25T22:49:59Z)
• PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion [80.79938369319152]
  We design a new pipeline coined PCF-Lift based on our Probabilis-tic Contrastive Fusion (PCF) Our PCF-lift not only significantly outperforms the state-of-the-art methods on widely used benchmarks including the ScanNet dataset and the Messy Room dataset (4.4% improvement of scene-level PQ)
  arXiv  Detail & Related papers  (2024-10-14T16:06:59Z)
• WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
  Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
  arXiv  Detail & Related papers  (2024-07-18T11:51:01Z)
• Learning Gaussian Representation for Eye Fixation Prediction [54.88001757991433]
  Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points. We introduce Gaussian Representation for eye fixation modeling. We design our framework upon some lightweight backbones to achieve real-time fixation prediction.
  arXiv  Detail & Related papers  (2024-03-21T20:28:22Z)
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution [67.9215891673174]
  We propose score entropy as a novel loss that naturally extends score matching to discrete spaces. We test our Score Entropy Discrete Diffusion models on standard language modeling tasks.
  arXiv  Detail & Related papers  (2023-10-25T17:59:12Z)
• Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection [4.721505041393889]
  We propose a spherical projection-based U-Net (SPU-Net) segmentation model design. Multiple independent segmentation predictions can be obtained from a single MRI. The model successfully achieved low uncertainty for correct segmentation predictions and high uncertainty for incorrect results.
  arXiv  Detail & Related papers  (2022-10-12T18:11:49Z)
• Characterizing and Taming Model Instability Across Edge Devices [4.592454933053539]
  This paper presents the first methodical characterization of the variations in model prediction across real-world mobile devices. We introduce a new metric, instability, which captures this variation. In experiments, 14-17% of images produced divergent classifications across one or more phone models.
  arXiv  Detail & Related papers  (2020-10-18T16:52:06Z)
• Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference [119.19779637025444]
  Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) This paper studies multi-exit networks associated with input-adaptive inference, showing their strong promise in achieving a "sweet point" in cooptimizing model accuracy, robustness and efficiency.
  arXiv  Detail & Related papers  (2020-02-24T00:40:22Z)
• Machine Learning Pipeline for Segmentation and Defect Identification from High Resolution Transmission Electron Microscopy Data [0.0]
  We demonstrate a flexible two step pipeline for analysis of high resolution transmission electron microscopy data. Our trained U-Net is able to segment nanoparticles from amorphous background with a Dice coefficient of 0.8. We are then able to classify whether nanoparticles contain a visible stacking fault with 86% accuracy.
  arXiv  Detail & Related papers  (2020-01-14T19:49:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.