Abstract
Speckle reconstruction is a classical inverse problem in computational imaging. Inspired by the memory effect of the scattering medium, deep learning methods reveal excellent performance in extracting the correlation of speckle patterns. Nowadays, advanced models generally include more than 10M parameters and mostly pay more attention to the spatial feature information. However, the frequency domain of images also contains precise hierarchical representations. Here we propose a one-to-all lightweight Fourier channel attention convolutional neural network (FCACNN) with Fourier channel attention and the res-connected bottleneck structure. Compared with the state-of-the-art model, i.e., self-attention armed convolutional neural network (SACNN), our architecture has better feature extraction and reconstruction ability. The Pearson correlation coefficient and Jaccard index scores of FCACNN increased by at least 5.2% and 13.6% compared with task-related models. And the parameter number of the lightweight FCACNN is only 1.15M. Furthermore, the validation results show that the one-to-all model, FCACNN, has excellent generalization capability on unseen speckle patterns such as handwritten letters and Quickdraws.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Yangyundou Wang, Zhaosu Lin, Hao Wang, Chuanfei Hu, Hui Yang, and Min Gu
Opt. Express 29(22) 35702-35711 (2021)
Zicheng Huang, Ziyu Gu, Mengyang Shi, Yesheng Gao, and Xingzhao Liu
Opt. Express 32(1) 444-456 (2024)
Lin Li, Peng Wang, Lingrui Wang, Changku Sun, and Luhua Fu
Opt. Express 32(6) 10715-10731 (2024)