Fengyan Gu

Fengyan Gu

Auto-generated profile, based on publicly available information

Fengyan Gu

Nanjing Normal University, 12534 Nanjing, Jiangsu China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 December 2019 in IEEE Photonics Journal
Verified
Journal Article
Open access
DYDa Yin
Da Yin
ZGZhongzheng Gu
Zhongzheng Gu
YZYanran Zhang
Yanran Zhang
FGFengyan Gu
Fengyan Gu
SNShouping Nie
Shouping Nie
CYCaojin Yuan
Caojin Yuan
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.