Deep-Learned Broadband Encoding Stochastic Filters for Computational Spectroscopic Instruments

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, a BEST-filter-based spectral camera presents a higher reconstruction accuracy with up to 30 times enhancement and a better tolerance to fabrication errors. The generalizability of PCSED is validated in designing metasurface- and interference-thin-film-based BEST filters.

Automated summary

A neural network-based framework called parameter constrained spectral encoder and decoder (PCSED) is presented for designing BEST filters in spectroscopic instruments, linking mathematical optimum and practical limits. This approach results in a spectral camera based on BEST filters with higher reconstruction accuracy and better tolerance to fabrication errors. PCSED's generalizability is validated in designing metasurface- and interference-thin-film-based BEST filters.