Joint Compression and Demosaicking for Satellite Images - UFR ISTIC Informatique et électronique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Joint Compression and Demosaicking for Satellite Images

Résumé

Image sensors used in real camera systems are equipped with colour filter arrays which sample the light rays in different spectral bands. Each colour channel can thus be obtained separately by considering the corresponding colour filter. While existing compression solutions mostly assume that the captured raw data has been demosaicked prior to compression, in this paper, we describe an end-to-end trainable neural network for joint compression and demosaicking of satellite images. We first introduce a training loss combining a perceptual loss with the classical mean square error, which is shown to better preserve the high-frequency details present in satellite images. We then present a multi-loss balancing strategy which significantly improves the performance of the proposed joint demosaicking-compression solution.
Fichier principal
Vignette du fichier
ICASSP_2023_BACCHUS.pdf (559.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04056997 , version 1 (03-04-2023)
hal-04056997 , version 2 (23-05-2023)

Identifiants

Citer

Pascal Bacchus, Renaud Fraisse, Aline Roumy, Christine Guillemot. Joint Compression and Demosaicking for Satellite Images. ICASSP 2023 - International Conference on Acoustics, Speech, and Signal Processing, Jun 2023, Rhodes (Grèce), Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096011⟩. ⟨hal-04056997v2⟩
60 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More