Scholarlink

<p>Event cameras, as novel bio-inspired neuromorphic sensors, detect per-pixel brightness changes asynchronously. Despite their growing popularity in various applications, their potential in X-ray imaging remains largely unexplored. Synchrotron-based X-ray imaging plays a significant role in various fields of science, technology and medicine. However, time-resolved imaging still faces several challenges in achieving higher sampling rates and managing the substantial data volume. Here, we introduce an inline dual-camera setup, which leverages a high-speed CMOS camera and an event camera, aiming to temporally super-resolve the sampled frame data using sparse events. To process the data, frames and events are first aligned pixel-by-pixel using feature matching, and then used to train a deep-learning neural network. This network effectively integrates the two modalities to reconstruct the intermediate frames, achieving up to a 6-fold temporal upsampling. Our work demonstrates an event-guided temporal super-resolution approach in the X-ray imaging domain, which unlocks possibilities for future time-resolved experiments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Event-guided temporally super-resolved synchrotron X-ray imaging

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月28日

查看全文
  • Hongjian Wang,
  • Alexander Hadjiivanov,
  • Emmanuel Blazquez,
  • Christian M. Schlepütz,
  • Marco Stampanoni,
  • Goran Lovric

摘要

Event cameras, as novel bio-inspired neuromorphic sensors, detect per-pixel brightness changes asynchronously. Despite their growing popularity in various applications, their potential in X-ray imaging remains largely unexplored. Synchrotron-based X-ray imaging plays a significant role in various fields of science, technology and medicine. However, time-resolved imaging still faces several challenges in achieving higher sampling rates and managing the substantial data volume. Here, we introduce an inline dual-camera setup, which leverages a high-speed CMOS camera and an event camera, aiming to temporally super-resolve the sampled frame data using sparse events. To process the data, frames and events are first aligned pixel-by-pixel using feature matching, and then used to train a deep-learning neural network. This network effectively integrates the two modalities to reconstruct the intermediate frames, achieving up to a 6-fold temporal upsampling. Our work demonstrates an event-guided temporal super-resolution approach in the X-ray imaging domain, which unlocks possibilities for future time-resolved experiments.