计算机科学
人工神经网络
光学
人工智能
图像处理
计算机视觉
信号处理
医学影像学
光学相干层析成像
图像质量
模式识别(心理学)
光学成像
空间频率
噪音(视频)
作者
yao wang,Muchen Zhu,Linjun Zhai,Huiyuan Zhang,Junnan Chen,Yiming Yu,Dajing Wang,Yang Zhaohua,Baolei Liu,Fan Wang
出处
期刊:Optics Letters
[Optica Publishing Group]
日期:2026-10-14
卷期号:51 (22): 6387-6390
摘要
Near-infrared (NIR) imaging has emerged as an important technology for night vision, remote sensing, and biological imaging, yet conventional array-detector-based systems are often limited by insufficient sensitivity, high cost, and substantial dark noise. Single-pixel imaging (SPI) offers an attractive alternative, enabling single-photon-level NIR imaging by using a cost-effective single-element detector. Nevertheless, SPI remains restricted by photon noise, leading to degraded imaging quality and limited frame rate under extremely low photon flux conditions. Here we introduce the Hessian-Sparsity Untrained Neural Network (HS-UNN) for robust photon-starved NIR imaging without pretraining. The HS-UNN integrates the physical forward model of SPI with an untrained neural network regularized by both sparsity priors and Hessian-based structural constraints, enabling effective noise suppression while preserving structural fidelity and continuity. Both simulated and experimental results demonstrate that HS-UNN enables high-quality reconstructions under ultra-low NIR photon levels down to ~0.01 photons per pixel per illumination pattern. Furthermore, we demonstrate its dynamic capability by monitoring the dynamic evolution and detachment of infrared-absorbing droplets with a data acquisition rate of ~20 Hz and offline image reconstruction under ~0.19 photons per pixel per illumination pattern, highlighting its potential for high-sensitivity near-infrared inspection. The proposed reconstruction framework paves the way for practical NIR imaging in extreme low-light conditions, which can be extended to visible, mid-infrared, or terahertz imaging, offering broad potential for photon-efficient sensing across a wide spectral range.
科研通智能强力驱动
Strongly Powered by AbleSci AI