Deep-Learned Broadband Encoding Stochastic Filters for Computational Spectroscopic Instruments
Abstract
Computational spectroscopic instruments with Broadband Encoding Stochastic (BEST) filters allow the reconstruction of the spectrum at high precision with only a few filters. However, conventional design manners of BEST filters are often heuristic and may fail to fully explore the encoding potential of BEST filters. The Parameter Constrained Spectral Encoder and Decoder (PCSED) - a neural network-based framework is presented for the design of BEST filters in spectroscopic instruments. By incorporating the target spectral response definition and the optical design procedures comprehensively, PCSED links the mathematical optimum and practical limits confined by available fabrication techniques. Benefiting from this, the BEST-filter-based spectral camera present a higher reconstruction accuracy with up to 30 times' enhancement and a better tolerance on fabrication errors. The generalizability of PCSED is validated in designing metasurface- and interference-thin-film-based BEST filters.
Cite
@article{arxiv.2012.09383,
title = {Deep-Learned Broadband Encoding Stochastic Filters for Computational Spectroscopic Instruments},
author = {Hongya Song and Yaoguang Ma and Yubing Han and Weidong Shen and Wenyi Zhang and Yanghui Li and Xu Liu and Yifan Peng and Xiang Hao},
journal= {arXiv preprint arXiv:2012.09383},
year = {2020}
}