Research map / Probabilistic and scientific modeling / Molecules and proteins
Optical Diffraction-based Convolution for Semiconductor Lithography
Young-Han Son, Dong-Hee Shin, Deok-Joong Lee, Hyun Jung Lee, Tae-Eui Kam
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Fresnel OP kernel (ablation) | OptiCo · StdContact (ViaSet OOD) | EPE: 22.612 -> 0.079 | Improved |
| add Fresnel OP kernel (ablation) | OptiCo · StdMetal (MetalSet OOD) | EPE: 2.819 -> 0.044 | Improved |
| use Fresnel or Green's kernel instead of Helmholtz/Hopkins (learnable weight) (ablation) | OptiCo · StdContact | EPE: 0.303 (Helmholtz) -> 0.079 (Fresnel) | Improved |
| use strict scalar-weight kernel: Hopkins vs Fresnel (ablation) | OptiCo · StdContact | EPE: Hopkins 0.212, Fresnel 1.061 | Mixed |
| add complex-domain ComplexConv1D alone (ablation) | OptiCo · StdContact | EPE: 22.612 -> 7.491 | Improved |
| add multiply-constants (MC) to OP convolution (ablation) | OptiCo · StdContact | EPE: 6.321 -> 1.273 | Improved |
| add ComplexConv1D to OP+MC (ablation) | OptiCo · StdContact | EPE: 1.273 -> 0.079 | Improved |
| add TV loss (ablation) | OptiCo · MetalSet mask optimization | shot count: 1523 -> 715 | Improved |
| add TV loss (ablation) | OptiCo · MetalSet mask optimization | EPE: 1.4 -> 1.6 | Hurt |
| add morphological post-processing to TV-loss masks vs no TV (ablation) | OptiCo · MetalSet | EPE: EPE +0.6 without TV loss vs +0.2 with TV loss | Improved |
| replace OptiCo block with FNO block (ablation) | OptiCo backbone · mask optimization | EPE | Hurt |
| use OptiCo vs ILILT | OptiCo · Mask optimization average | MSE: 22143 -> 14535 | Improved |
Closest papers by meaning
- ILILT: Implicit Learning of Inverse Lithography Technologies (ICML 2024 · similarity 0.86)
- Neural Tangent Knowledge Distillation for Optical Convolutional Networks (NeurIPS 2025 · similarity 0.86)
- OpticalNet: An Optical Imaging Dataset and Benchmark Beyond the Diffraction Limit (CVPR 2025 · similarity 0.85)
- All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising (CVPR 2025 · similarity 0.84)
- Optical Diffusion Models for Image Generation (NeurIPS 2024 · similarity 0.83)
- Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
