EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution

Matteo Kolyszko iD, Marco Buzzelli iD, Simone Bianco iD, Raimondo Schettini iD

Journal of Imaging · 28.01.2026 · 12 (2) · 61

DOI: 10.3390/jimaging12020061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 28.01.2026. Verfasst von Matteo Kolyszko und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, 20125 Milan, Italy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PNRR-NGEU.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral imaging (HSI) enables fine spectral analysis but is often limited by low spatial resolution due to sensor constraints. To address this, we propose CGNet, a color-guided hyperspectral super-resolution network that leverages complementary information from low-resolution hyperspectral inputs and high-resolution RGB images. CGNet adopts a dual-encoder design: the RGB encoder extracts hierarchical spatial features, while the HSI encoder progressively upsamples spectral features. A multi-scale fusion decoder then combines both modalities in a coarse-to-fine manner to reconstruct the high-resolution HSI. Training is driven by a hybrid loss that balances L1 and Spectral Angle Mapper (SAM), which ablation studies confirm as the most effective formulation. Experiments on two benchmarks, ARAD1K and StereoMSI, at ×4 and ×6 upscaling factors demonstrate that CGNet consistently outperforms state-of-the-art baselines. CGNet achieves higher PSNR and SSIM, lower SAM, and reduced ΔE00, confirming its ability to recover sharp spatial structures while preserving spectral fidelity.

Schlagwörter

Stichwörter der Autor:innen

RGB guidancedeep learninghyperspectral imagingimage fusionsuper-resolution

Autor:innen und Institutionen

  • Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, 20125 Milan, Italy.

ORCID-Profile: Matteo Kolyszko, Marco Buzzelli, Simone Bianco, Raimondo Schettini

Förderung

  • PNRR-NGEU

Zitieren

APA

Kolyszko, M., Buzzelli, M., Bianco, S., & Schettini, R. (2026). Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution. Journal of Imaging, 12(2), 61. https://doi.org/10.3390/jimaging12020061

Vancouver

Kolyszko M, Buzzelli M, Bianco S, Schettini R. Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution. Journal of Imaging. 2026;12(2):61. doi:10.3390/jimaging12020061

BibTeX
@article{Kolyszko2026,
  author = {Kolyszko, Matteo and Buzzelli, Marco and Bianco, Simone and Schettini, Raimondo},
  title = {Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {2},
  pages = {61},
  doi = {10.3390/jimaging12020061}
}
Kostenlos starten →