Abstract

We adopted an unpaired neural network training technique, namely CycleGAN, to generate bright-field microscope-like images from hologram reconstructions. The motivation for unpaired training in microscope applications is that the construction of paired/parallel datasets is cumbersome or sometimes not even feasible, for example, lensless or flow-through holographic measuring setups. Our results show that the proposed method is applicable in these cases and provides comparable results to the paired training. Furthermore, it has some favorable properties even though its metric scores are lower. The CycleGAN training results in sharper and—from this point of view—more realistic object reconstructions compared to the baseline paired setting. Finally, we show that a lower metric score of the unpaired training does not necessarily imply a worse image generation but a correct object synthesis, yet with a different focal representation.

© 2021 Optical Society of America

PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets

Yuhe Zhang, Mike Andreas Noack, Patrik Vagovic, Kamel Fezzaa, Francisco Garcia-Moreno, Tobias Ritschel, and Pablo Villanueva-Perez
Opt. Express 29(13) 19593-19604 (2021)

Deep-learning-based computer-generated hologram from a stereo image pair

Chenliang Chang, Di Wang, Dongchen Zhu, Jiamao Li, Jun Xia, and Xiaolin Zhang
Opt. Lett. 47(6) 1482-1485 (2022)

Lensless computational imaging with a hybrid framework of holographic propagation and deep learning

Zhiming Tian, Zhao Ming, Aobing Qi, Fengqiang Li, Xining Yu, and Yongxin Song
Opt. Lett. 47(17) 4283-4286 (2022)

High-speed computer-generated holography using an autoencoder-based deep neural network

Jiachen Wu, Kexuan Liu, Xiaomeng Sui, and Liangcai Cao
Opt. Lett. 46(12) 2908-2911 (2021)

Deep-learning-based hyperspectral recovery from a single RGB image

Junchao Zhang, Yuanyuan Sun, Jianlai Chen, Degui Yang, and Rongguang Liang
Opt. Lett. 45(20) 5676-5679 (2020)