Abstract
Reconstruction algorithms are at the forefront of accessible and compact data collection. In this paper, we present a novel reconstruction algorithm, SpecRA, that adapts based on the relative rarity of a signal compared to previous observations. We leverage a data-driven approach to learn optimal encoder-array sensitivities for a novel filter-array spectrometer. By taking advantage of the regularities mined from diverse online repositories, we are able to exploit low-dimensional patterns for improved spectral reconstruction from as few as p=2 channels. Furthermore, the performance of SpecRA is largely independent of signal complexity. Our results illustrate the superiority of our method over conventional approaches and provide a framework towards "fourth paradigm" spectral sensing. We hope that this work can help reduce the size, weight and cost constraints of future spectrometers for specific spectral monitoring tasks in applied contexts such as in remote sensing, healthcare, and quality control.