期刊
IEEE PHOTONICS JOURNAL
卷 12, 期 2, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JPHOT.2019.2961137
关键词
Holography; deep learning; phase recovery; aberration
资金
- National Science Foundation of China (NSFC) [61775097, 61975081]
- National key research and development program [2017YFB0503505]
- Open Foundation of Key Lab of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education [2017VGE02]
Convolutional neural network (CNN) has great potentials in holographic reconstruction. Although excellent results can be achieved by using this technique, the number of training and label data must be the same and strict paired relationship is required. Here, we present a new end-to-end learning-based framework to reconstruct noise-free images in absence of any paired training data and prior knowledge of object real distribution. The algorithm uses the cycle consistency loss and generative adversarial network to implement unpaired training method. It is demonstrated by the experiments that high accuracy reconstruction images can be obtained by using unpaired training and label data. Moreover, the unpaired feature of the algorithm makes the system robust to displacement aberration and defocusing effect.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据