Abstract

Channeled spectropolarimetry (CSP) employing low-pass channel extraction filters suffers from cross talk and spectral resolution loss. These are aggravated by empirically defining the shape and scope of the filters for different measured. Here, we propose a convolutional deep-neural-network-based channel filtering framework for spectrally–temporally modulated CSP. The network is trained to adaptively predict spectral magnitude filters (SMFs) that possess wide bandwidths and anti-cross-talk features that adapt to scene data in the two-dimensional Fourier domain. Mixed filters that combine the advantages of low-pass filters and SMFs demonstrate superior performance in reconstruction accuracy.

© 2021 Optical Society of America

Spectral–temporal hybrid modulation for channeled spectropolarimetry

Qiwei Li, Andrey S. Alenin, and J. Scott Tyo
Appl. Opt. 59(30) 9359-9367 (2020)

Temporal and spectral unmixing of photoacoustic signals by deep learning

Yifeng Zhou, Fenghe Zhong, and Song Hu
Opt. Lett. 46(11) 2690-2693 (2021)

Deep-learning-based adaptive camera calibration for various defocusing degrees

Jing Zhang, Bin Luo, Zhuolong Xiang, Qican Zhang, Yajun Wang, Xin Su, Jun Liu, Lu Li, and Wei Wang
Opt. Lett. 46(22) 5537-5540 (2021)

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)

Holographic and speckle encryption using deep learning

Xiaogang Wang, Wenqi Wang, Haoyu Wei, Bijun Xu, and Chaoqing Dai
Opt. Lett. 46(23) 5794-5797 (2021)