InSPECtor: an end-to-end design framework for compressive pixelated hyperspectral instruments
T.A. Stockmans, F. Snik, M. Esposito, C. van Dijk, C.U. Keller

TL;DR
This paper presents InSPECtor, a framework for designing compressive hyperspectral imagers that optimize sensor micro-patterns and reconstruction algorithms jointly, significantly reducing data volume while preserving information.
Contribution
It introduces a novel end-to-end optimization framework for hyperspectral sensors that combines micro-patterned filter design with reconstruction, enabling high compression ratios.
Findings
Achieves up to 40x data reduction compared to traditional methods.
Demonstrates effective joint optimization using TensorFlow's automatic differentiation.
Provides optimized sensor layouts for various spectral and spatial sampling configurations.
Abstract
Classic designs of hyperspectral instrumentation densely sample the spatial and spectral information of the scene of interest. Data may be compressed after the acquisition. In this paper we introduce a framework for the design of an optimized, micro-patterned snapshot hyperspectral imager that acquires an optimized subset of the spatial and spectral information in the scene. The data is thereby compressed already at the sensor level, but can be restored to the full hyperspectral data cube by the jointly optimized reconstructor. This framework is implemented with TensorFlow and makes use of its automatic differentiation for the joint optimization of the layout of the micro-patterned filter array as well as the reconstructor. We explore the achievable compression ratio for different numbers of filter passbands, number of scanning frames, and filter layouts using data collected by the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
