EUVIMEDEUVIMED entdecken
Crossref

Learnable foveated sampling and dual-prior reconstruction for single-pixel imaging

Xin Huang, Qiurong Yan, Dawei Song, Zhenyang Xiong, Zheyu Fang, Junyuan Yin, Xule Dai, Xinhong Luo

Optics Express · 13.07.2026 · 34 (14) · 25946

DOI: 10.1364/oe.601620 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 07.07.2026. Verfasst von Xin Huang und 7 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Jiangxi Provincial Department of Science and Technology, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-pixel imaging (SPI) is a low-cost, high-sensitivity compressed sensing technique with broad application prospects. Most existing deep learning-based SPI reconstruction methods adopt a uniform sampling strategy. They fail to fully exploit the flexibly programmable nature of sampling patterns in SPI. Inspired by the high-resolution perception mechanism of the fovea in biological vision systems, we propose a deep network called FDP_Net. This network jointly optimizes foveated sampling and dual-prior reconstruction. First, we design a learnable foveal sampling module that adaptively performs high-resolution sampling on the image center region and low-resolution aggregated sampling on the periphery. Thus, under a limited total number of measurements, it equivalently increases the sampling rate of the center region. Second, we construct a deep unfolding reconstruction network with dual-prior fusion. It integrates a sparse prior module (SPM) and a denoising prior module (DPM) in a cascade manner. This enables more comprehensive capture of image texture and structure information. In addition, we introduce a center-weighted differential loss function. This loss function guides the network to prioritize the reconstruction quality of the region of interest. Experimental results show that our method achieves significantly better reconstruction accuracy in the image center region than mainstream comparison methods. Finally, we binarize the trained sampling matrix. The proposed method is successfully validated on a real single-photon counting SPI microscopy system.

Förderung

  • Jiangxi Provincial Department of Science and Technology
  • National Natural Science Foundation of China

Zitieren

APA

Huang, X., Yan, Q., Song, D., Xiong, Z., Fang, Z., Yin, J., Dai, X., & Luo, X. (2026). Learnable foveated sampling and dual-prior reconstruction for single-pixel imaging. Optics Express, 34(14), 25946. https://doi.org/10.1364/oe.601620

Vancouver

Huang X, Yan Q, Song D, Xiong Z, Fang Z, Yin J, et al. Learnable foveated sampling and dual-prior reconstruction for single-pixel imaging. Optics Express. 2026;34(14):25946. doi:10.1364/oe.601620

BibTeX
@article{Huang2026,
  author = {Huang, Xin and Yan, Qiurong and Song, Dawei and Xiong, Zhenyang and Fang, Zheyu and Yin, Junyuan and Dai, Xule and Luo, Xinhong},
  title = {Learnable foveated sampling and dual-prior reconstruction for single-pixel imaging},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {14},
  pages = {25946},
  doi = {10.1364/oe.601620}
}
Kostenlos starten →