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

Robust contrast-transfer-function phase retrieval via flexible deep learning networks

Chen Bai, Meiling Zhou, Junwei Min, Shipei Dang, Xianghua Yu, Peng Zhang, Tong Peng, and Baoli Yao
Opt. Lett. 44(21) 5141-5144 (2019)

Nonlinear primal–dual algorithm for the phase and absorption retrieval from a single phase contrast image

Kannara Mom, Max Langer, and Bruno Sixou
Opt. Lett. 47(20) 5389-5392 (2022)

Lensless phase retrieval based on deep learning used in holographic data storage

Jianying Hao, Xiao Lin, Yongkun Lin, Haiyang Song, Ruixian Chen, Mingyong Chen, Kun Wang, and Xiaodi Tan
Opt. Lett. 46(17) 4168-4171 (2021)

Phase retrieval via nonlocal complex-domain sparsity

Liheng Bian, Xin Wang, Xuyang Chang, Zhijie Gao, and Tong Qin
Opt. Lett. 48(7) 1854-1857 (2023)

Real-time phase imaging with physics-enhanced network and equivariance

Yuheng Wang, Huiyang Wang, Chengxin Zhou, Xianxin Han, Shengde Liu, Xiaoxu Lu, Jianglei Di, and Liyun Zhong
Opt. Lett. 48(10) 2732-2735 (2023)