Selected Publications

Selected research in multimodal imaging, hyperspectral acquisition, and reconstruction.

2026

Cross-modal registration and confidence-aware RGB-guided hyperspectral fusion

Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment

Mohamad Jouni, Aurélien Godet and Mauro Dalla Mura

Conference British Machine Vision Conference (BMVC), 2026

Cross-modal alignment and confidence-aware fusion improve RGB-guided hyperspectral super-resolution under real camera misalignment with a low computational footprint.

arXiv HAL Details Programme
BibTeX 
@inproceedings{JouniGD26:bmvc,
  title = {Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment},
  author = {Mohamad Jouni and Aurélien Godet and Mauro Dalla Mura},
  booktitle = {British Machine Vision Conference},
  year = {2026},
  url = {https://arxiv.org/abs/2609.01060}
}
Encoder and decoder adapters surrounding a pretrained RGB denoiser

Leveraging pretrained RGB denoisers for hyperspectral image restoration

Daniele Picone, Mohamad Jouni and Mauro Dalla Mura

Conference IEEE International Conference on Image Processing (ICIP), 2026

Lightweight adapters reuse frozen pretrained RGB denoisers for hyperspectral restoration through spectral projections and learned reconstruction.

Paper arXiv HAL Details
BibTeX 
@inproceedings{PiconeJD26:icip,
  title = {Leveraging pretrained RGB denoisers for hyperspectral image restoration},
  author = {Daniele Picone and Mohamad Jouni and Mauro Dalla Mura},
  booktitle = {IEEE International Conference on Image Processing},
  year = {2026},
  url = {https://ieeexplore.ieee.org/abstract/document/11630149}
}

2025

Cocoa bean scenes acquired with four cameras and annotated by fermentation quality

A Multimodal hyperspectral dataset of cocoa beans with physicochemical annotation

Kebin Contreras, Mohamad Jouni, Mauro Dalla Mura and Jorge Bacca

Journal Nature Scientific Data (Sci. Data), 2025

A multimodal cocoa-bean dataset combines spectral images from four cameras with physicochemical measurements to support non-invasive quality assessment.

Paper HAL Code Dataset Details
BibTeX 
@article{ContrerasJDB25:scidata,
  title = {A Multimodal hyperspectral dataset of cocoa beans with physicochemical annotation},
  author = {Kebin Contreras and Mohamad Jouni and Mauro Dalla Mura and Jorge Bacca},
  journal = {Nature Scientific Data},
  year = {2025},
  url = {https://www.nature.com/articles/s41597-025-06314-9}
}