Scholarlink

<p>Ghost imaging (GI) enables 2D image reconstruction by leveraging high-order correlation between 1D bucket signals and 2D light field information. It demonstrates enhanced detection sensitivity and high-quality image reconstruction via efficient photon collection in scattering media. Recent studies have established that deep learning (DL) can substantially enhance the GI reconstruction quality. Furthermore, with the emergence of large models such as SDXL and GPT-4, the constraints of conventional DL in parameters and architecture have been transcended, enabling models to comprehensively explore relationships among all distinct positions within feature sequences. This paradigm shift has significantly advanced the capability of DL in restoring severely degraded and low-resolution imagery, making it particularly advantageous for noise-robust image reconstruction in GI applications. In this paper, we propose the first large imaging model with 1.4 billion parameters that incorporates the physical principles of GI (GILM). The proposed GILM implements a skip connection mechanism to mitigate gradient explosion challenges inherent in deep architectures, ensuring sufficient parametric capacity to capture intricate correlations between single-pixel measurements and the object. Moreover, GILM leverages multi-head attention mechanism to learn spatial dependencies across pixel points during image reconstruction, facilitating the extraction of comprehensive object information for subsequent reconstruction. We validated the effectiveness of GILM through a series of experiments, including simulated object imaging, imaging objects in free space, and imaging objects located 52 m away in an underwater environment. The experimental results demonstrate that GILM effectively captures the fluctuation trends of the collected signals, thereby facilitating accurate reconstruction of the object’s image from the acquired data. Finally, GILM was successfully deployed on a portable computing platform, demonstrating its feasibility for practical engineering applications.</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

Large model enhanced computational ghost imaging

  • 期刊论文

  • 发表日期：

    2025年10月27日

查看全文
  • Yifan Chen,
  • Hongjun An,
  • Zhe Sun,
  • Tong Tian,
  • Mingliang Chen,
  • Christian Spielmann,
  • Xuelong Li

摘要

Ghost imaging (GI) enables 2D image reconstruction by leveraging high-order correlation between 1D bucket signals and 2D light field information. It demonstrates enhanced detection sensitivity and high-quality image reconstruction via efficient photon collection in scattering media. Recent studies have established that deep learning (DL) can substantially enhance the GI reconstruction quality. Furthermore, with the emergence of large models such as SDXL and GPT-4, the constraints of conventional DL in parameters and architecture have been transcended, enabling models to comprehensively explore relationships among all distinct positions within feature sequences. This paradigm shift has significantly advanced the capability of DL in restoring severely degraded and low-resolution imagery, making it particularly advantageous for noise-robust image reconstruction in GI applications. In this paper, we propose the first large imaging model with 1.4 billion parameters that incorporates the physical principles of GI (GILM). The proposed GILM implements a skip connection mechanism to mitigate gradient explosion challenges inherent in deep architectures, ensuring sufficient parametric capacity to capture intricate correlations between single-pixel measurements and the object. Moreover, GILM leverages multi-head attention mechanism to learn spatial dependencies across pixel points during image reconstruction, facilitating the extraction of comprehensive object information for subsequent reconstruction. We validated the effectiveness of GILM through a series of experiments, including simulated object imaging, imaging objects in free space, and imaging objects located 52 m away in an underwater environment. The experimental results demonstrate that GILM effectively captures the fluctuation trends of the collected signals, thereby facilitating accurate reconstruction of the object’s image from the acquired data. Finally, GILM was successfully deployed on a portable computing platform, demonstrating its feasibility for practical engineering applications.