HSI-SC-NeRF: NeRF-based hyperspectral 3D reconstruction using a stationary camera for agricultural applications
Frontiers in Plant Science · 30.10.2026 · 17
DOI: 10.3389/fpls.2026.1960204 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 30.10.2026. Verfasst von Kibon Ku und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, United States. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Food and Agriculture, Directorate for Biological Sciences, Plant Sciences Institute, Iowa State University.
Abstract (Originalsprache)
Introduction
Advances in hyperspectral Q5 imaging (HSI) and 3D reconstruction have enabled accurate characterization of agricultural produce quality and plant phenotypes, both essential for advancing agricultural sustainability and breeding programs. However, integrating these two modalities at scale remains challenging, as conventional approaches involve complex hardware setups incompatible with automated phenotyping systems. Recent advances in neural radiance fields (NeRF) offer computationally efficient 3D reconstruction but typically require moving-camera setups, limiting throughput and reproducibility in standard indoor agricultural environments. To address these challenges, we introduce HSI-SC-NeRF, a stationary-camera multi-channel NeRF framework for high-throughput hyperspectral 3D reconstruction targeting postharvest inspection of agricultural produce.
Methods
Multi-view hyperspectral data is captured using a stationary camera while the object rotates within a custom-built Teflon imaging chamber providing diffuse, uniform illumination. Cameraposes are estimated via structure-from-motion using ArUco fiducial markers as persistent features, then transformed from the object frame to the camera frame through simulated pose transformation, enabling standard NeRF training on stationary camera data. A multi-channel NeRF formulation optimizes reconstruction across all hyperspectral bands jointly using a composite spectral loss, supported by a two-stage training protocol that decouples geometric initialization from radiometric refinement to improve spectral fidelity.
Results
On a representative sample, the reconstruction achieves a close geometric agreement with an independent reference reconstruction; across diverse agricultural samples, it achieves strong spectral fidelity across the visible and near-infrared spectrum, supporting its use in automated agricultural workflows.
Discussion
The full 204-band reconstruction additionally enables exploration of literature-informed wavelength bands, facilitating redeployment with faster multispectral cameras for high-throughput production environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, United States.
- Department of Mechanical Engineering, Iowa State University, Ames, IA, United States.
Förderung
- National Institute of Food and Agriculture
- Directorate for Biological Sciences
- Plant Sciences Institute, Iowa State University
Zitieren
APA
Ku, K., Jubery, T., Krishnamurthy, A., & Ganapathysubramanian, B. (2026). HSI-SC-NeRF: NeRF-based hyperspectral 3D reconstruction using a stationary camera for agricultural applications. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1960204
Vancouver
Ku K, Jubery T, Krishnamurthy A, Ganapathysubramanian B. HSI-SC-NeRF: NeRF-based hyperspectral 3D reconstruction using a stationary camera for agricultural applications. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1960204
BibTeX
@article{Ku2026,
author = {Ku, Kibon and Jubery, Talukder and Krishnamurthy, Adarsh and Ganapathysubramanian, Baskar},
title = {HSI-SC-NeRF: NeRF-based hyperspectral 3D reconstruction using a stationary camera for agricultural applications},
journal = {Frontiers in Plant Science},
year = {2026},
volume = {17},
doi = {10.3389/fpls.2026.1960204}
}
EUVIMED