Hessian-sparsity untrained neural network for near-infrared single-photon, single-pixel imaging
Optics Letters · 15.11.2026 · 51 (22) · 6387
DOI: 10.1364/ol.612479 ↗Kurz gefasst
Leserbrief in der Zeitschrift Optics Letters, online erschienen am 12.11.2026. Verfasst von Yao Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics, Beihang University, Beijing 100191, China. Die Arbeit nennt 25 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
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.
Autor:innen und Institutionen
- School of Physics, Beihang University, Beijing 100191, China.
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing 100191, China.
- Hangzhou International Innovation Institute, Beihang University, Hangzhou 311115, China.
ORCID-Profile: Dajing Wang, Zhaohua Yang, Baolei Liu
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wang, Y., Zhu, M., Zhai, L., Zhang, H., Chen, J., Yu, Y., Wang, D., Yang, Z., Liu, B., & Wang, F. (2026). Hessian-sparsity untrained neural network for near-infrared single-photon, single-pixel imaging. Optics Letters, 51(22), 6387. https://doi.org/10.1364/ol.612479
Vancouver
Wang Y, Zhu M, Zhai L, Zhang H, Chen J, Yu Y, et al. Hessian-sparsity untrained neural network for near-infrared single-photon, single-pixel imaging. Optics Letters. 2026;51(22):6387. doi:10.1364/ol.612479
BibTeX
@article{Wang2026,
author = {Wang, Yao and Zhu, Muchen and Zhai, Linjun and Zhang, Huiyuan and Chen, Junnan and Yu, Yiming and Wang, Dajing and Yang, Zhaohua and Liu, Baolei and Wang, Fan},
title = {Hessian-sparsity untrained neural network for near-infrared single-photon, single-pixel imaging},
journal = {Optics Letters},
year = {2026},
volume = {51},
number = {22},
pages = {6387},
doi = {10.1364/ol.612479}
}
EUVIMED