Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.21911 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912978709774336 |
|---|---|
| author | Azizi, Chedly Ben Guilloteau, Claire Roussel, Gilles Puigt, Matthieu |
| author_facet | Azizi, Chedly Ben Guilloteau, Claire Roussel, Gilles Puigt, Matthieu |
| contents | Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a latent generative representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder (VAE) pretraining with parameter-to-latent interpolation. Experiments on PROSAIL-simulated vegetation data and Sentinel-3 OLCI imagery demonstrate that the method outperforms classical regression-based emulators in reconstruction accuracy, spectral fidelity, and robustness to real-world spatial variability. We further show that emulated HSIs preserve performance in downstream biophysical parameter retrieval, highlighting the practical relevance of emulated data for remote sensing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Latent Representation Learning Framework for Hyperspectral Image Emulation in Remote Sensing Azizi, Chedly Ben Guilloteau, Claire Roussel, Gilles Puigt, Matthieu Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a latent generative representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder (VAE) pretraining with parameter-to-latent interpolation. Experiments on PROSAIL-simulated vegetation data and Sentinel-3 OLCI imagery demonstrate that the method outperforms classical regression-based emulators in reconstruction accuracy, spectral fidelity, and robustness to real-world spatial variability. We further show that emulated HSIs preserve performance in downstream biophysical parameter retrieval, highlighting the practical relevance of emulated data for remote sensing applications. |
| title | A Latent Representation Learning Framework for Hyperspectral Image Emulation in Remote Sensing |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2603.21911 |