Abstract:The vast majority of transmission electron microscopy (TEM) data never gets published and ends up on a backup drive until deleted to free up space. These left-over datasets are rich in detail and variation, often paired with automatically saved metadata of instrument state and acquisition parameters. In this work, we introduce a dataset of 7,330 high-angle annular dark-field scanning-TEM (HAADF-STEM) images from a single instrument to learn a joint embedding space between image metadata and HAADF image. These embeddings link image style with acquisition parameters, which allows us to train a generative style transfer network that can convert experimental images into the style they would have had if they were recorded with different instrument parameters. We evaluate the performance of the network and explore the usefulness of the technique for physical denoising.
| Subjects: | Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2604.24909 [cs.LG] |
| (or arXiv:2604.24909v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.24909 arXiv-issued DOI via DataCite (pending registration) |
From: Georgia Channing [view email]
[v1]
Mon, 27 Apr 2026 18:42:07 UTC (9,137 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。