Abstract
We demonstrate for the first time that deep neural networks (DNNs) can be trained to recover images transported through a 90 cm-long silica-air disordered optical fiber at variable working distances without any distal optics.
© 2018 The Author(s)
PDF ArticleMore Like This
Jian Zhao, Yangyang Sun, Zheyuan Zhu, Jose Enrique Antonio-Lopez, Rodrigo Amezcua Correa, Shuo Pang, and Axel Schülzgen
SoW1H.2 Specialty Optical Fibers (SOF) 2018
Jian Zhao, Yangyang Sun, Zheyuan Zhu, Donghui Zheng, Jose Enrique Antonio-Lopez, Rodrigo Amezcua Correa, Shuo Pang, and Axel Schülzgen
CW3B.6 Computational Optical Sensing and Imaging (COSI) 2018
Jian Zhao, Yangyang Sun, Jose Enrique Antonio-Lopez, Rodrigo Amezcua Correa, Shuo Pang, and Axel Schülzgen
STh3L.2 CLEO: Science and Innovations (CLEO:S&I) 2019