Semantic based generative compression of images for extremely low bitrates - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Semantic based generative compression of images for extremely low bitrates

Résumé

We propose a framework for image compression in which the fidelity criterion is replaced by a semantic and quality preservation objective. Encoding the image thus becomes a simple extraction of semantic, enabling to reach drastic compression ratio. The decoding side is handled by a generative model relying on the diffusion process for the reconstruction of images. We first propose to describe the semantic using low resolution segmentation maps as guide. We further improve the generation, introducing colors map guidance without retraining the generative decoder. We show that it is possible to produce images of high visual quality with preserved semantic at extremely low bitrates when compared with classical codecs.
Fichier principal
Vignette du fichier
Semantic_based_generative_compression_of_images-7.pdf (6.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04231421 , version 1 (06-10-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04231421 , version 1

Citer

Tom Bordin, Thomas Maugey. Semantic based generative compression of images for extremely low bitrates. MMSP 2023 - IEEE 25th International Workshop on MultiMedia Signal Processing, Sep 2023, Poitiers, France. pp.1-6. ⟨hal-04231421⟩
74 Consultations
44 Téléchargements

Partager

Gmail Facebook X LinkedIn More