Single-pixel imaging using physics enhanced deep learning

作     者：FEI WANG CHENGLONG WANG CHENJIN DENG SHENSHENG HAN GUOHAI SITU FEI WANG;CHENGLONG WANG;CHENJIN DENG;SHENSHENG HAN;GUOHAI SITU

作者机构：Shanghai Institute of Optics and Fine MechanicsChinese Academy of SciencesShanghai 201800China Center of Materials Science and Optoelectronics EngineeringUniversity of Chinese Academy of SciencesBeijing 100049China Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China 

出 版 物：《Photonics Research》 (光子学研究（英文版）)

年 卷 期：2022年第10卷第1期

页      面：104-110页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China(61991452, 62061136005) Key Research Program of Frontier Sciences of the Chinese Academy of Sciences(QYZDB-SSW-JSC002) Chinesisch-Deutsche Zentrum für Wissenschaftsf?rderung (GZ1391) 

主　　题：SPI image illumination 

摘      要：Single-pixel imaging(SPI) is a typical computational imaging modality that allows two-and three-dimensional image reconstruction from a one-dimensional bucket signal acquired under structured *** is in particular of interest for imaging under low light conditions and in spectral regions where good cameras are ***,the resolution of the reconstructed image in SPI is strongly dependent on the number of measurements in the temporal ***-driven deep learning has been proposed for high-quality image reconstruction from a undersampled bucket *** the generalization issue prohibits its practical *** we propose a physics-enhanced deep learning approach for *** blending a physics-informed layer and a model-driven fine-tuning process,we show that the proposed approach is generalizable for image *** implement the proposed method in an in-house SPI system and an outdoor single-pixel LiDAR system,and demonstrate that it outperforms some other widespread SPI algorithms in terms of both robustness and *** proposed method establishes a bridge between data-driven and model-driven algorithms,allowing one to impose both data and physics priors for inverse problem solvers in computational imaging,ranging from remote sensing to microscopy.