Contents
1 Issue (s), 1 Article (s)
Vol. 2, Iss.3—May.1, 2025 • pp: 031001- Spec. pp:
Export citation format
Vol. 2, Iss.3-May..1,2025
Edge accelerated reconstruction using sensitivity analysis for single-lens computational imaging
Xuquan Wang, Tianyang Feng, Yujie Xing, Ziyu Zhao... and Xinbin Cheng|Show fewer author(s)
Computational imaging enables high-quality infrared imaging using simple and compact optical systems. However, the integration of specialized reconstruction algorithms introduces additional latency and increases computational and power demands, which impedes the performance of high-speed, low-power optical applications, such as unmanned aerial vehicle (UAV)-based remote sensing and biomedical imaging. Traditional model compression strategies focus primarily on optimizing network complexity and multiply-accumulate operations (MACs), but they overlook the unique constraints of computational imaging and the specific requirements of edge hardware, rendering them inefficient for computational camera implementation. In this work, we propose an edge-accelerated reconstruction strategy based on end-to-end sensitivity analysis for single-lens infrared computational cameras. Compatibility-based operator reconfiguration, sensitivity-aware pruning, and sensitivity-aware mixed quantization are employed on edge-artificial intelligence (AI) chips to balance inference speed and reconstruction quality. The experimental results show that, compared to the traditional approach without hardware feature guidance, the proposed strategy achieves better performance in both reconstruction quality and speed, with reduced complexity and fewer MACs. Our single-lens computational camera with edge-accelerated reconstruction demonstrates high-quality, video-level imaging capability in field experiments. This work is dedicated to addressing the practical challenge of real-time edge reconstruction, paving the way for lightweight, low-latency computational imaging applications.Computational imaging enables high-quality infrared imaging using simple and compact optical systems. However, the integration of specialized reconstruction algorithms introduces additional latency and increases computational and power demands, which impedes the performance of high-speed, low-power optical applications, such as unmanned aerial vehicle (UAV)-based remote sensing and biomedical imaging. Traditional model compression strategies focus primarily on optimizing network complexity and multiply-accumulate operations (MACs), but they overlook the unique constraints of computational imaging and the specific requirements of edge hardware, rendering them inefficient for computational camera implementation. In this work, we propose an edge-accelerated reconstruction strategy based on end-to-end sensitivity analysis for single-lens infrared computational cameras. Compatibility-based operator reconfiguration, sensitivity-aware pruning, and sensitivity-aware mixed quantization are employed on edge-artificial intelligence (AI) chips to balance inference speed and reconstruction quality. The experimental results show that, compared to the traditional approach without hardware feature guidance, the proposed strategy achieves better performance in both reconstruction quality and speed, with reduced complexity and fewer MACs. Our single-lens computational camera with edge-accelerated reconstruction demonstrates high-quality, video-level imaging capability in field experiments. This work is dedicated to addressing the practical challenge of real-time edge reconstruction, paving the way for lightweight, low-latency computational imaging applications.
Advanced Imaging
- Publication Date: May. 30, 2025
- Vol. 2, Issue 3, 031001 (2025)
Emerging Coding Method for Computational Imaging (2025)
Submission Open:1 April 2025; Submission Deadline: 1 August 2025
Editor (s): Xin Yuan, David Brady, Enrique Tajahuerce, Jinli Suo... Liang Gao and Ni Chen|Show fewer author(s)
Vol. 2, Issue 2, 021001 (2025)
Privacy-preserving face recognition with a mask-encoded microlens array
Vol. 2, Issue 1, 011001 (2025)
Ultrahigh-speed schlieren photography via diffraction-gated real-time mappingOn the Cover
Vol. 2, Issue 1, 015001 (2025)
Vol. 1, Issue 2, 021002 (2024)
Real-time 3D imaging based on ROI fringe projection and a lightweight phase-estimation network
Vol. 1, Issue 2, 021004 (2024)
Future-proof imaging: computational imaging
Vol. 1, Issue 1, 012001 (2024)
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20