# Super-r'esolution non supervis'ee d'images hyperspectrales de t'el'ed'etection utilisant un entrainement enti`erement synth'etique

arXiv: https://arxiv.org/abs/2602.02552 · HTML: https://mlsanity.com/paper/2602.02552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery](https://mlsanity.com/paper/2005.08752/) (2020)
- [Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separation](https://mlsanity.com/paper/1310.7529/) (2013)
- [Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion](https://mlsanity.com/paper/2205.03742/) (2022)
- [Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-Resolution](https://mlsanity.com/paper/2007.14007/) (2020)
- [Unrolling PALM for sparse semi-blind source separation](https://mlsanity.com/paper/2112.05694/) (2021)
- [Provably robust blind source separation of linear-quadratic near-separable mixtures](https://mlsanity.com/paper/2011.11966/) (2020)
- [Unsupervised Super-Resolution of Hyperspectral Remote Sensing Images Using Fully Synthetic Training](https://mlsanity.com/paper/2601.16602/) (2026)

## Abstract (arXiv)

Hyperspectral single image super-resolution (SISR) aims to enhance spatial resolution while preserving the rich spectral information of hyperspectral images. Most existing methods rely on supervised learning with high-resolution ground truth data, which is often unavailable in practice. To overcome this limitation, we propose an unsupervised learning approach based on synthetic abundance data. The hyperspectral image is first decomposed into endmembers and abundance maps through hyperspectral unmixing. A neural network is then trained to super-resolve these maps using data generated with the dead leaves model, which replicates the statistical properties of real abundances. The final super-resolution hyperspectral image is reconstructed by recombining the super-resolved abundance maps with the endmembers. Experimental results demonstrate the effectiveness of our method and the relevance of synthetic data for training.