EUVIMEDEUVIMED entdecken
Crossref

K-FISTA: a Kronecker-domain FISTA unrolling network for flexible single-pixel imaging across sampling ratios and multiple image resolutions

Xiangping Li, Zhi Qin, Haojie Li, Kaicheng Zhou, Xudong Yang, Shenghai Hu, Tao Xu, Xiaoqing Jia, Xuecou Tu, Labao Zhang, Qingyuan Zhao, Lin Kang und 2 weitere

Optics Express · 13.07.2026 · 34 (14) · 26470

DOI: 10.1364/oe.607402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 08.07.2026. Verfasst von Xiangping Li und 13 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: Quantum Science and Technology-National Science and Technology Major Project, National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-pixel imaging (SPI) has attracted considerable attention due to its simple hardware architecture and broad spectral adaptability. However, achieving high-quality SPI reconstruction that robustly adapts to varying sampling ratios and multiple image resolutions remains a challenge. To address this, we propose K-FISTA, a Kronecker-domain fast iterative shrinkage-thresholding algorithm (FISTA) unrolling network for flexible SPI reconstruction. The proposed framework follows a FISTA-inspired unrolling paradigm under the Kronecker compressed sensing model and reformulates momentum extrapolation, gradient descent, and prior modeling as learnable modules. Specifically, a tensor-form gradient descent step enforces measurement fidelity directly in the two-dimensional image domain, avoiding the construction of large-scale vectorized sensing matrices. A cross-stage state momentum refinement (CSMR) module adaptively exploits historical reconstruction information, while a deep restoration prior equipped with multi-branch global modeling and channel attention calibration enhances structural and textural recovery. Additionally, an explicit restoration target supervision strategy is introduced to guide progressive reconstruction across unfolding stages. Extensive simulated and real-world experiments demonstrate that K-FISTA enables accurate, efficient, and flexible SPI reconstruction using a single trained model across sampling ratios from 1% to 50% and multiple image resolutions, including 128 × 128, 256 × 256, 321 × 481, and 512 × 512. Notably, on the Set11 dataset, K-FISTA obtains PSNR/SSIM values of 22.93 dB/0.6426 at a 1% sampling ratio and 28.33 dB/0.8475 at a 4% sampling ratio, highlighting its robustness in severely undersampled regimes and practical adaptability to varying acquisition settings.

Förderung

  • Quantum Science and Technology-National Science and Technology Major Project
  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Fundamental Research Funds for the Central Universities
  • Priority Academic Program Development of Jiangsu Higher Education Institutions
  • Key Lab of Optoelectronic Devices and System with Extreme Performance, MOE
  • Jiangsu Key Laboratory of Advanced Manipulating Technique of Electromagnetic Waves

Zitieren

APA

Li, X., Qin, Z., Li, H., Zhou, K., Yang, X., Hu, S., Xu, T., Jia, X., Tu, X., Zhang, L., Zhao, Q., Kang, L., Chen, J., & Wu, P. (2026). K-FISTA: a Kronecker-domain FISTA unrolling network for flexible single-pixel imaging across sampling ratios and multiple image resolutions. Optics Express, 34(14), 26470. https://doi.org/10.1364/oe.607402

Vancouver

Li X, Qin Z, Li H, Zhou K, Yang X, Hu S, et al. K-FISTA: a Kronecker-domain FISTA unrolling network for flexible single-pixel imaging across sampling ratios and multiple image resolutions. Optics Express. 2026;34(14):26470. doi:10.1364/oe.607402

BibTeX
@article{Li2026,
  author = {Li, Xiangping and Qin, Zhi and Li, Haojie and Zhou, Kaicheng and Yang, Xudong and Hu, Shenghai and Xu, Tao and Jia, Xiaoqing and Tu, Xuecou and Zhang, Labao and Zhao, Qingyuan and Kang, Lin and Chen, Jian and Wu, Peiheng},
  title = {K-FISTA: a Kronecker-domain FISTA unrolling network for flexible single-pixel imaging across sampling ratios and multiple image resolutions},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {14},
  pages = {26470},
  doi = {10.1364/oe.607402}
}
Kostenlos starten →