Learning to see high-density random images long-term transmitted in multimode fiber
Xueqing Li,
Binbin Song,
Jixuan Wu,
Wei Lin,
Wei Huang,
Bo Liu,
Xinliang Gao
Affiliations
Xueqing Li
The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), The Key Laboratory of Computer Vision and Systems (Ministry of Education), and The School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China
Binbin Song
The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), The Key Laboratory of Computer Vision and Systems (Ministry of Education), and The School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China
Jixuan Wu
Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems, School of Electronic and Information Engineering, Tiangong University, Tianjin 300387, China
Wei Lin
Institute of Modern Optics, Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin 300350, China
Wei Huang
The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education), The Key Laboratory of Computer Vision and Systems (Ministry of Education), and The School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China
Bo Liu
Institute of Modern Optics, Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin 300350, China
Xinliang Gao
Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems, School of Electronic and Information Engineering, Tiangong University, Tianjin 300387, China
An improved multi-channel symmetric network (MCSNet) is proposed to reconstruct high-channel-density random images after long-term transmission through multimode fibers (MMFs). Temporal correlation within a period of 25 minutes is calculated to investigate the time-varying characteristics of speckles. The results demonstrated that due to noise accumulation along the MMF path, the quality of speckles deteriorates significantly after long-term transmission. The MCSNet integrates U-Net and ConvNeXt Block, which enables to more fully extract the features of each channel within the entire speckle. After being trained by different random image datasets within the initial moment, tests on random images and realistic scenes of endoscopic surgery after 25 min of transmission are carried out, and all of them demonstrate a near-perfect reconstruction performance and superior scalability, which indicates that MCSNet is suitable for long-term imaging demodulation of endoscopes.
