Advanced Photonics Nexus, Volume. 3, Issue 2, 026010(2024)

Physics-constrained deep-inverse point spread function model: toward non-line-of-sight imaging reconstruction

Su Wu1、†, Chan Huang2, Jing Lin3, Tao Wang1,4, Shanshan Zheng1,4, Haisheng Feng1,4, and Lei Yu1、*
Author Affiliations
  • 1Chinese Academy of Sciences, Anhui Institute of Optics and Fine Mechanics, Hefei, China
  • 2Hefei University of Technology, School of Physics, Department of Optical Engineering, Hefei, China
  • 3Hefei Normal University, Department of Chemical and Chemical Engineering, Hefei, China
  • 4University of Science and Technology of China, Science Island Branch of Graduate School, Hefei, China
  • show less
    Figures & Tables(11)
    The NLOS system and reconstruction principle. (a) A confocal NLOS imaging system with a CMOS camera to capture the image. (b) The imaging equation in an optical system with PSF and (c) propagation process from object to image in the NLOS system.
    Light path in the NLOS system. (a) Wavefront propagation process of diffuse reflection and (b) definition of diffuse reflection parameters.
    Flowchart of PCIN algorithm for NLOS imaging reconstruction. The speckle image captured by the camera is put into CNN, and PCIN iteratively updates the parameters in CNN using the loss function constructed by the speckle image and forward physical model. The optimized parameters are utilized to obtain a high-quality reconstructed image.
    Back and front of the experimental scene. Light passes from the laser, to the collimator, to the wall, to the hidden object, and finally to the camera.
    Comparison of the reconstructed images of various exposure time from the proposed PCIN method. (a) Speckle images of different exposure time captured by the camera. (b) Ground truth. (c) Reconstructed images of different exposure time.
    Comparison of the reconstructed images of various exposure time from the proposed PCIN method. (a) Speckle images of different exposure time captured by the camera. (b) Ground truth. (c) Reconstructed images of different exposure time.
    Comparison of the reconstructed cartoon images and Chinese characters of various exposure time from the proposed PCIN method. (a) Speckle images of different exposure time captured by the camera. (b) Ground truth. (c) Reconstructed images of different exposure time.
    Comparison of the reconstructed images of convex, concave, and wavy walls.
    Comparison of the reconstructed images of PR, CNN, and PCIN methods at 40 ms exposure time.
    Comparison of the reconstructed images of PR, CNN, and PCIN methods after a 10 deg change in image plane inclination.
    Comparison of the reconstructed images of PR, CNN, and PCIN methods at 20 ms exposure time.
    Tools

    Get Citation

    Copy Citation Text

    Su Wu, Chan Huang, Jing Lin, Tao Wang, Shanshan Zheng, Haisheng Feng, Lei Yu. Physics-constrained deep-inverse point spread function model: toward non-line-of-sight imaging reconstruction[J]. Advanced Photonics Nexus, 2024, 3(2): 026010

    Download Citation

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

    Category: Research Articles

    Received: Nov. 8, 2023

    Accepted: Feb. 27, 2024

    Published Online: Mar. 19, 2024

    The Author Email: Yu Lei (yulei@aiofm.ac.cn)

    DOI:10.1117/1.APN.3.2.026010

    Topics