Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 4 min ago
Peer-reviewedCC BYLight Science & Applications

High-accuracy hyperspectro-polarimetric real-time imaging via a deep learning empowered infrared meta-sensor

  • Huiming Luo1,2,3
  • Jie Deng2,3
  • Jing Zhou4,5,6
  • Tianyuan Cui7,2
  • Yuejie Zhang2,3
  • Junwei Huang2,3
  • Liwen Fu2,3
  • Yonghao Bu2
  • Ruowen Wang2,3
  • Mengdie Shi2,3
  • Xiaofei He2,3
  • Xueling Guo2,3
3 more authors
  • Jun Ning2,3
  • Xiaoshuang Chen8,9,10,11
  • Wei Lü12,13,14,15
15 affiliations
  1. 1School of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China
  2. 2State Key Laboratory of Infrared Physics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China
  3. 3University of Chinese Academy of Sciences, Beijing, 101408, China
  4. 4Shanghai Key Laboratory of Optical Coatings and Spectral Modulation, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China. [email protected]
  5. 5State Key Laboratory of Infrared Physics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China. [email protected]
  6. 6University of Chinese Academy of Sciences, Beijing, 101408, China. [email protected]
  7. 7School of Physical Science and Technology, ShanghaiTech University, Shanghai, 201210, China
  8. 8School of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China. [email protected]
  9. 9State Key Laboratory of Infrared Physics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China. [email protected]
  10. 10Suzhou Laboratory, Suzhou, 215000, Jiangsu, China. [email protected]
  11. 11University of Chinese Academy of Sciences, Beijing, 101408, China. [email protected]
  12. 12School of Physical Science and Technology, ShanghaiTech University, Shanghai, 201210, China. [email protected]
  13. 13School of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China. [email protected]
  14. 14State Key Laboratory of Infrared Physics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China. [email protected]
  15. 15University of Chinese Academy of Sciences, Beijing, 101408, China. [email protected]
Open at sourcePDFDOICite

Abstract

Light inherently carries multidimensional information, including intensity, polarization, and spectrum. Employing a miniaturized device to simultaneously, instantaneously, and accurately capture the multidimensional information of incident light in a single exposure holds significant applications across numerous fields, but remains challenging. Here, we demonstrate high-accuracy hyperspectro-full-Stokes-polarimetric real-time imaging across a broad wavelength range (1150-1650 nm) with 167 spectral channels, via a metasurface integrated near infrared camera empowered by a residual attention network. The metasurface, which simultaneously performs polarization multiplexing and spectral dispersion, functions as a multidimensional encoder. A tailored deep learning network with a residual attention module is established and trained to reconstruct the multidimensional information of incident light with high accuracy. The key performance metrics-including spectral and image resolution, as well as spectral and polarization reconstruction accuracy-all surpass the best-reported specifications of hyperspectro-polarimetric cameras, with enhancements ranging from several-fold to one order of magnitude. Based on this approach, even intricately coupled multidimensional information can be resolved. In addition, the acquisition, processing, and inference time only takes 18 ms, allowing high-dimensional hyperspectral-polarimetric imaging at 55 frames per second in real time. This work offers a promising solution enabling high-accuracy hyperspectro-polarimetric real-time imaging with a compact camera.

Related

  1. Deep learning-empowered metasurface design for complex target ISAR illusions
    Cheng Zhu, Shaozhong Fu, Wang Xu +3
    Optics ExpressPeer-reviewedPublisher termsMaterials & polymersCrossref
  2. Machine Learning-Empowered Electromagnetic Wave Absorbing Materials: From Forward Prediction to Generative Inverse Design
    Tongbaihui Qi, Jie Zhou
    MoleculesPeer-reviewedCC BY6 citedMaterials & polymersOpenAlex
  3. Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
    Modupe A. Omoniyi
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  4. Flexible On-the-Fly Active Learning for Molecular Infrared Spectra.
    Giulio Benedini, Matti Hellström, Lucas Visscher
    Journal of chemical theory and computationPeer-reviewedCC BYFull textMaterials & polymersEurope PMC
  5. Accuracy and Efficiency Benchmarks of Pretrained Machine Learning Potentials for Molecular Simulations
    Peter K. Eastman, Evan Pretti, Thomas E. Markland
    Journal of Chemical Theory and ComputationPeer-reviewedCC BY-NC-NDFull text8 citedMaterials & polymersOpenAlex

Cite

BibTeXRIS
BibTeX
@article{luo2026highaccuracy,
  title = {{High-accuracy hyperspectro-polarimetric real-time imaging via a deep learning empowered infrared meta-sensor}},
  author = {Huiming Luo and Jie Deng and Jing Zhou and Tianyuan Cui and Yuejie Zhang and Junwei Huang and Liwen Fu and Yonghao Bu and Ruowen Wang and Mengdie Shi and Xiaofei He and Xueling Guo and Jun Ning and Xiaoshuang Chen and Wei Lü},
  journal = {Light Science \& Applications},
  year = {2026},
  month = aug,
  doi = {10.1038/s41377-026-02407-1},
  url = {https://doi.org/10.1038/s41377-026-02407-1},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - High-accuracy hyperspectro-polarimetric real-time imaging via a deep learning empowered infrared meta-sensor
AU  - Huiming Luo
AU  - Jie Deng
AU  - Jing Zhou
AU  - Tianyuan Cui
AU  - Yuejie Zhang
AU  - Junwei Huang
AU  - Liwen Fu
AU  - Yonghao Bu
AU  - Ruowen Wang
AU  - Mengdie Shi
AU  - Xiaofei He
AU  - Xueling Guo
AU  - Jun Ning
AU  - Xiaoshuang Chen
AU  - Wei Lü
PY  - 2026
DA  - 2026/08/20
JO  - Light Science & Applications
DO  - 10.1038/s41377-026-02407-1
UR  - https://doi.org/10.1038/s41377-026-02407-1
AB  - Light inherently carries multidimensional information, including intensity, polarization, and spectrum. Employing a miniaturized device to simultaneously, instantaneously, and accurately capture the multidimensional information of incident light in a single exposure holds significant applications across numerous fields, but remains challenging. Here, we demonstrate high-accuracy hyperspectro-full-Stokes-polarimetric real-time imaging across a broad wavelength range (1150-1650 nm) with 167 spectral channels, via a metasurface integrated near infrared camera empowered by a residual attention network. The metasurface, which simultaneously performs polarization multiplexing and spectral dispersion, functions as a multidimensional encoder. A tailored deep learning network with a residual attention module is established and trained to reconstruct the multidimensional information of incident light with high accuracy. The key performance metrics-including spectral and image resolution, as well as spectral and polarization reconstruction accuracy-all surpass the best-reported specifications of hyperspectro-polarimetric cameras, with enhancements ranging from several-fold to one order of magnitude. Based on this approach, even intricately coupled multidimensional information can be resolved. In addition, the acquisition, processing, and inference time only takes 18 ms, allowing high-dimensional hyperspectral-polarimetric imaging at 55 frames per second in real time. This work offers a promising solution enabling high-accuracy hyperspectro-polarimetric real-time imaging with a compact camera.
SN  - 2047-7538
SN  - 2095-5545
ER  -