Image restoration for optical synthetic aperture system via variational physics-informed network

Bu Ning; Mei Hui; Ming Liu; Liquan Dong; Lingqin Kong; Yuejin Zhao

Results in Physics (Sep 2023)

Image restoration for optical synthetic aperture system via variational physics-informed network

Bu Ning,
Mei Hui,
Ming Liu,
Liquan Dong,
Lingqin Kong,
Yuejin Zhao

Affiliations

Bu Ning: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China
Mei Hui: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Corresponding author at: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
Ming Liu: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China
Liquan Dong: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China
Lingqin Kong: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China
Yuejin Zhao: School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China; Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing 100081, China; Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China

Journal volume & issue: Vol. 52
p. 106878

Abstract

Read online

Optical synthetic aperture with homogeneous circular sub-mirrors greatly improves the spatial resolution of space telescopes; however, the discrete and sparse characteristics of the sub-mirrors reduce the mid-frequency modulation transfer function (MTF), resulting in blurred images being obtained. In this paper, a method combining variational physics-informed with deep learning is presented, which shows blind image restoration without complex priors. The constraint effect of traditional maximum a posterior (MAP) framework is removed by variational inference framework, which is embedded into Variational Physics-informed Network (VPIN) to optimize neural network training. Residual dense blocks (RDBs) construction is contributed to image feature extraction. Networks with SSIM-corrected loss functions can be trained at the feature level to help with convergence. When SNR = 30 dB, the PSNR of Golay-6 remote sensing test set increases from 20.16 dB to 23.90 dB, SSIM is from 0.610 to 0.842, and MS-SSIM is from 0.930 to 0.955.

Published in Results in Physics

ISSN: 2211-3797 (Online)
Publisher: Elsevier
Country of publisher: Netherlands
LCC subjects: Science: Physics
Website: http://www.journals.elsevier.com/results-in-physics/

About the journal

Abstract

Keywords