Accelerating 4D hyperspectral imaging through physics-informed neural representation and adaptive sampling
Optics Express · 24.08.2026 · 34 (17) · 31736
DOI: 10.1364/oe.599405 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 13.08.2026. Verfasst von Chi-Jui Ho und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Air Force Office of Scientific Research.
Abstract (Originalsprache)
High-dimensional hyperspectral imaging (HSI) enables the visualization of ultrafast molecular dynamics and complex, heterogeneous spectra. However, applying this capability to resolve spatially varying vibrational couplings in two-dimensional infrared (2DIR) spectroscopy, a type of coherent multidimensional spectroscopy (CMDS), necessitates prohibitively long data acquisition, driven by dense Nyquist sampling requirements and the need for extensive signal accumulation. To address this challenge, we introduce a physics-informed neural representation approach that efficiently reconstructs dense spatially resolved 2DIR hyperspectral images from sparse experimental measurements. In particular, we use a multilayer perceptron (MLP) to model the relationship between the sub-sampled 4D coordinates and their corresponding spectral intensities, and to recover densely sampled 4D spectra from limited observations. The reconstruction results demonstrate that our method, using a fraction of the samples, faithfully recovers both oscillatory and non-oscillatory spectral dynamics in experimental measurements. Moreover, we develop a loss-aware adaptive sampling method to progressively introduce potentially informative samples for iterative data collection while conducting experiments. Experimental results show that the proposed approach achieves high-fidelity spectral recovery with only 1/32 of the sampling budget, compared with exhaustive sampling, thereby reducing total experimental time by up to 32-fold. This framework offers a scalable solution for accelerating experiments involving hypercube data, including multidimensional spectroscopy and hyperspectral imaging, paving the way for rapid chemical imaging of transient biological and material systems.
Förderung
- Air Force Office of Scientific Research
Zitieren
APA
Ho, C., Bhakta, H., Xiong, W., & Antipa, N. (2026). Accelerating 4D hyperspectral imaging through physics-informed neural representation and adaptive sampling. Optics Express, 34(17), 31736. https://doi.org/10.1364/oe.599405
Vancouver
Ho C, Bhakta H, Xiong W, Antipa N. Accelerating 4D hyperspectral imaging through physics-informed neural representation and adaptive sampling. Optics Express. 2026;34(17):31736. doi:10.1364/oe.599405
BibTeX
@article{Ho2026,
author = {Ho, Chi-Jui and Bhakta, Harsh and Xiong, Wei and Antipa, Nicholas},
title = {Accelerating 4D hyperspectral imaging through physics-informed neural representation and adaptive sampling},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {17},
pages = {31736},
doi = {10.1364/oe.599405}
}
EUVIMED