MUSE: A Multi-view Synthesis Enhancer - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

MUSE: A Multi-view Synthesis Enhancer

Nour Hobloss
  • Fonction : Auteur
  • PersonId : 1108849
Jérôme Fournier
Nicolas Ramin
  • Fonction : Auteur
  • PersonId : 1290831

Résumé

In this paper, we introduce the MUSE (MUlti-view Synthesis Enhancer) method, which is an evolution of our previously proposed HDSB method and is based on a hybrid algorithmic-learning-based scheme. MUSE generates novel views of a scene using an autoencoder specifically optimized for refining pre-synthesized views that have been derived from actual observations. Since the subjective test is the ultimate test of the visual rendering quality, we evaluate our proposed method by two subjective tests. Experimental results show that the MUSE brings a global gain compared to two tested state-of-the-art methods.
Fichier principal
Vignette du fichier
Final_version.pdf (26.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04356701 , version 1 (22-01-2024)

Identifiants

Citer

Nour Hobloss, Joshua Maraval, Jérôme Fournier, Nicolas Ramin, Lu Zhang. MUSE: A Multi-view Synthesis Enhancer. 2023 31st European Signal Processing Conference (EUSIPCO), Sep 2023, Helsinki, Finland. ⟨10.23919/eusipco58844.2023.10289903⟩. ⟨hal-04356701⟩
25 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More