GAN architecture leveraging a Retinex model with colored illumination for low-light image restoration - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Access Année : 2023

GAN architecture leveraging a Retinex model with colored illumination for low-light image restoration

Résumé

In this work, we study the restoration of low-light images with outdoor scenes without ground truth. Until now, approaches in the literature have avoided using the Retinex decomposition model in an unsupervised way or have added constraining priors on the searched components. We propose here to relax the constraint of a grayscale illumination of the Retinex model. Indeed, according to the physics of light, it should include a colored illumination. Resulting from this new decomposition model, we formulate a new deep learning-based architecture inspired by the style transfer methods. Our method enables us to visualize the illumination (i.e. a complex style with the same dimensions as an image) and the reflectance (i.e. the content). It achieves more visually pleasing components compared to the state-of-the-art i.e. without artifact, without noise amplification and without hallucination with a simple restoration for each of the components.
Fichier principal
Vignette du fichier
Retinex_GAN-2.pdf (19.22 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04184198 , version 1 (21-08-2023)

Licence

Paternité

Identifiants

Citer

Arthur Lecert, Aline Roumy, Renaud Fraisse, Christine Guillemot. GAN architecture leveraging a Retinex model with colored illumination for low-light image restoration. IEEE Access, 2023, 11, pp.84574 - 84588. ⟨10.1109/ACCESS.2023.3301614⟩. ⟨hal-04184198⟩
20 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More