X-ray fluorescence (XRF) microscopy is a powerful technique for quantifying the distribution of elements in complex materials, which makes it a crucial imaging technique across a wide range of disciplines in physical and biological sciences, including chemistry, materials science, microbiology, and geosciences. However, as a scanning microscopy technique, the spatial resolution of XRF imaging is inherently constrained by the x-ray probe profile and scanning step size. Here we propose a dual-branch machine learning (ML) model, which can extract scale-variant features and bypass abundant low-frequency information separately, to enhance the spatial resolution of the XRF images by mitigating the effects of blurring from the probe profile. The model is trained by simulated natural images, and a two-stage training strategy is used to overcome the domain gap between the natural images and experimental data. The tomography reconstruction from enhanced XRF projections shows an improvement in resolution by a scale factor of four and reveals distinct internal features invisible in low-resolution XRF within a battery sample. This study offers a promising approach for obtaining high-resolution XRF imaging from its low-resolution version, paving the way for future investigations in a broader range of disciplines and materials.

中文翻译：

---

通过双分支网络深度学习增强超分辨率 X 射线荧光显微镜

X 射线荧光 (XRF) 显微镜是一种用于量化复杂材料中元素分布的强大技术，这使其成为物理和生物科学广泛学科的关键成像技术，包括化学、材料科学、微生物学和地球科学。然而，作为一种扫描显微镜技术，XRF 成像的空间分辨率本质上受到 X 射线探头轮廓和扫描步长的限制。在这里，我们提出了一种双分支机器学习（ML）模型，该模型可以提取尺度变化特征并分别绕过丰富的低频信息，通过减轻探针轮廓模糊的影响来增强 XRF 图像的空间分辨率。该模型通过模拟自然图像进行训练，并采用两阶段训练策略来克服自然图像和实验数据之间的域差距。增强型 XRF 投影的断层扫描重建显示分辨率提高了四倍，并揭示了电池样品中低分辨率 XRF 中不可见的独特内部特征。这项研究提供了一种从低分辨率版本获得高分辨率 XRF 成像的有前途的方法，为未来在更广泛的学科和材料中的研究铺平了道路。