用U-Net提升低统计量μ子散射断层成像质量，让短时间扫描更实用。
U-Net Based Image Enhancement for Short-time Muon Scattering Tomography
- 基于模拟数据训练的U-Net框架，用于增强μ子散射断层成像的点最近接近位置图
- 实验数据上SSIM从0.7232提升至0.9699，LPIPS从0.3604降至0.0270
- 适合需要快速、高质成像的核安保与工业无损检测场景
μ子散射断层成像（MST）是一种有前景的非侵入式检测技术，但短时间扫描因μ子通量有限导致图像质量差，制约实际应用。为此，我们提出一种基于U-Net的框架，使用仿真重建的点最近接近位置（PoCA）图像进行训练，以提升图像质量。应用于实验MST数据后，该方法显著改善成像效果：结构相似性指数（SSIM）从0.7232提升至0.9699，学习感知图像块相似性（LPIPS）从0.3604降至0.0270。结果表明，该方法能有效增强低统计量下的MST图像，为短时间MST的实际部署铺平道路。
原文摘要 · Abstract (English)
Muon Scattering Tomography (MST) is a promising non-invasive inspection technique, yet the practical application of short-time MST is hindered by poor image quality due to limited muon flux. To address this limitation, we propose a U-Net-based framework trained on Point of Closest Approach (PoCA) images reconstructed with simulation MST data to enhance image quality. When applied to experimental MST data, the framework significantly improves image quality, increasing the Structural Similarity Index Measure (SSIM) from 0.7232 to 0.9699 and decreasing the Learned Perceptual Image Patch Similarity (LPIPS) from 0.3604 to 0.0270. These results demonstrate that our method can effectively enhance low-statistics MST images, thereby paving the way for the practical deployment of short-time MST.
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。