We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. PhISM outperforms prior methods on several classification and regression benchmarks, requires limited labeled data, and provides additional insights thanks to interpretable latent representation.
@article{arxiv.2508.21618,
title = {Physics-Informed Spectral Modeling for Hyperspectral Imaging},
author = {Zuzanna Gawrysiak and Krzysztof Krawiec},
journal= {arXiv preprint arXiv:2508.21618},
year = {2026}
}
Comments
Copyright 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works