Custom Structure Preservation in Face Aging - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Custom Structure Preservation in Face Aging

Guillermo Gomez-Trenado
  • Fonction : Auteur
Pablo Mesejo
  • Fonction : Auteur
Óscar Cordón
  • Fonction : Auteur

Résumé

In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We disentangle the style and content of the input image and propose a new decoder network that adopts a style-based strategy to combine the style and content representations of the input image while conditioning the output on the target age. We go beyond existing aging methods allowing users to adjust the degree of structure preservation in the input image during inference. To this purpose, we introduce a masking mechanism, the CUstom Structure Preservation module, that distinguishes relevant regions in the input image from those that should be discarded. CUSP requires no additional supervision. Finally, our quantitative and qualitative analysis which include a user study, show that our method outperforms prior art and demonstrates the effectiveness of our strategy regarding image editing and adjustable structure preservation. Code and pretrained models are available at https://github.com/guillermogotre/CUSP.

Dates et versions

hal-04205001 , version 1 (12-09-2023)

Identifiants

Citer

Guillermo Gomez-Trenado, Stéphane Lathuilière, Pablo Mesejo, Óscar Cordón. Custom Structure Preservation in Face Aging. European Conference on Computer Vision, 2022, Tel AViv, Israel. ⟨hal-04205001⟩
2 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More