Image Denoising for Wafer Transmission Electron Microscopy Using Segment Anything-Guided Optimization

Wafer transmission electron microscopy (TEM) images have gained significant attention for analyzing the internal structure of wafers. However, accurate measurements are often hindered by substantial errors because of unknown noise in these images. Therefore, image denoising is essential for reliable measurements of wafer TEM images. Denoising wafer TEM images, however, is particularly challenging because their noise characteristics differ significantly from those of typical images. Moreover, the absence of clean-noisy image pairs reduces the effectiveness of machine learning-based methods. To address this challenge, we propose a Segment Anything (SAM)guided optimization-based wafer TEM image denoising framework (SAMOD) that combines filter-based denoised images generated with various hyperparameter settings. By optimizing the combination weights using pseudo-measurement points identified by the vision foundation model SAM, SAMOD reduces measurement errors across six different semiconductor process images. Notably, SAMOD achieved competitive performance without requiring prior knowledge of noise characteristics or measurement information, time-consuming hyperparameter searches, or model training, ensuring both practicality and robustness.