A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration - Archive ouverte HAL
Conference Papers Year : 2021

A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration

Abstract

Hyperspectral imaging offers new perspectives for diverse applications, ranging from the monitoring of the environment using airborne or satellite remote sensing, precision farming, food safety, planetary exploration, or astrophysics. Unfortunately, the spectral diversity of information comes at the expense of various sources of degradation, and the lack of accurate ground-truth "clean" hyperspectral signals acquired on the spot makes restoration tasks challenging. In particular, training deep neural networks for restoration is difficult, in contrast to traditional RGB imaging problems where deep models tend to shine. In this paper, we advocate instead for a hybrid approach based on sparse coding principles that retains the interpretability of classical techniques encoding domain knowledge with handcrafted image priors, while allowing to train model parameters end-to-end without massive amounts of data. We show on various denoising benchmarks that our method is computationally efficient and significantly outperforms the state of the art.
Fichier principal
Vignette du fichier
main.pdf (8.82 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03423559 , version 1 (17-11-2021)

Identifiers

Cite

Théo Bodrito, Alexandre Zouaoui, Jocelyn Chanussot, Julien Mairal. A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration. NeurIPS 2021 – 35th Annual Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia. pp.5430-5442, ⟨10.5555/3540261.3540676⟩. ⟨hal-03423559⟩
136 View
46 Download

Altmetric

Share

More