Abstract
We propose the deep Gauss–Newton (DGN) algorithm. The DGN allows one to take into account the knowledge of the forward model in a deep neural network by unrolling a Gauss–Newton optimization method. No regularization or step size needs to be chosen; they are learned through convolutional neural networks. The proposed algorithm does not require an initial reconstruction and is able to retrieve simultaneously the phase and absorption from a single-distance diffraction pattern. The DGN method was applied to both simulated and experimental data and permitted large improvements of the reconstruction error and of the resolution compared with a state-of-the-art iterative method and another neural-network-based reconstruction algorithm.
© 2023 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Chen Bai, Meiling Zhou, Junwei Min, Shipei Dang, Xianghua Yu, Peng Zhang, Tong Peng, and Baoli Yao
Opt. Lett. 44(21) 5141-5144 (2019)
Kannara Mom, Max Langer, and Bruno Sixou
Opt. Lett. 47(20) 5389-5392 (2022)
Jianying Hao, Xiao Lin, Yongkun Lin, Haiyang Song, Ruixian Chen, Mingyong Chen, Kun Wang, and Xiaodi Tan
Opt. Lett. 46(17) 4168-4171 (2021)