用二值化输入让模型更好理解真实芯片图像，提升几何生成精度。
Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
- 将真实SEM图像二值化后输入视觉语言模型，聚焦几何结构。
- 在MIIC数据集上Dice系数从0.4393提升至0.5256，显著缩小仿真到现实差距。
- 适合做半导体检测数据增强的研究者和工业界工程师使用。
电路几何的精确参数控制对半导体检测至关重要，但获取足够真实的训练数据成本高昂。尽管扩散模型和生成对抗网络等生成模型可扩充训练数据，却难以保证计量任务所需的纳米级几何精度。本文提出一种视觉程序合成框架：利用视觉语言模型（VLM）将检测图像转换为可编辑的领域特定语言（DSL）代码，实现对电路几何的精准参数控制与数据生成。由于VLM仅在合成的DSL渲染数据上训练，处理真实扫描电子显微镜（SEM）图像时存在领域差异。为此，我们引入输入二值化策略，剥离SEM特有的纹理与噪声，使模型专注于几何结构。在MIIC数据集上，二值化输入使平均Dice系数从0.4393提升至0.5256，证明简单的纹理抽象能有效缓解仿真到现实的差距。
原文摘要 · Abstract (English)
Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly. Although generative models such as diffusion models and Generative Adversarial Networks (GANs) can augment training data, they cannot guarantee the nanometer-scale geometric accuracy required for metrology tasks. We propose a visual program synthesis framework in which a Vision-Language Model (VLM) converts inspection images into editable Domain-Specific Language (DSL) code describing circuit geometries, enabling controlled generation of training data with exact parameter manipulation. Because the VLM is trained solely on synthetic DSL-rendered data, a domain gap arises when processing real Scanning Electron Microscope (SEM) images. We bridge this gap with an input binarization strategy that strips SEM-specific texture and noise, letting the model focus on geometric structure. On the MIIC dataset, binarized inputs improve the mean Dice coefficient from 0.4393 to 0.5256 over the raw-input baseline, demonstrating that simple texture abstraction substantially mitigates the sim-to-real gap.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。