Infrared and Laser Engineering, Volume. 53, Issue 2, 20230252(2024)

Infrared image super-resolution based on spatially variant blur kernel calibration

Junfeng Cao1,2,3,4, Qinghai Ding5, and Haibo Luo1,2,3
Author Affiliations
  • 1Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China
  • 2Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
  • 3Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
  • 4University of Chinese Academy of Sciences, Beijing 100049, China
  • 5Space Star Technology Co., Ltd., Beijing 100086, China
  • show less
    Figures & Tables(11)
    (a) Multi-circle target; (b) Image acquisition environment based on parallel light tube; (c) A target image acquired by an infrared camera
    (a) Image coordinate system; (b) Target coordinate system
    Overall architecture of proposed blur kernel estimation network
    Schematic diagram of super-resolution reconstruction
    (a) Cropped portions of the images captured by long-focus infrared camera (a) and short-focus infrared camera (b) and synthesized high-resolution image
    Estimated blur kernels of long-focus infrared camera (a) and short-focus infrared camera (b)
    Visual results of different methods on real-world images captured by long-focus infrared camera for scale factor 4
    Visual results of different methods on real-world images captured by short-focus infrared camera for scale factor 4
    Visual results of different methods on 4-bar target image captured by long-focus infrared camera for scale factor 4
    • Table 1. Quantitative comparison with other methods with scale factor 4

      View table
      View in Article

      Table 1. Quantitative comparison with other methods with scale factor 4

      MethodNIQE↓PIQE↓BRISQUE↓
      Bicubic6.05889.93653.372
      MANet+RRDB-SFT4.88683.85252.723
      Ours4.57482.94849.394
    • Table 2. Total number of parameters and runtime of each step

      View table
      View in Article

      Table 2. Total number of parameters and runtime of each step

      StepParams/MRuntime/s
      HR target im synthesis-67.318
      Blur kernel estimation2.331.148
      Super-resolution reconstruction17.01622.645
    Tools

    Get Citation

    Copy Citation Text

    Junfeng Cao, Qinghai Ding, Haibo Luo. Infrared image super-resolution based on spatially variant blur kernel calibration[J]. Infrared and Laser Engineering, 2024, 53(2): 20230252

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Apr. 20, 2023

    Accepted: --

    Published Online: Mar. 27, 2024

    The Author Email:

    DOI:10.3788/IRLA20230252

    Topics