StyleGAN-based heatmap generator for face alignment with limited training data - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

StyleGAN-based heatmap generator for face alignment with limited training data

Philippe-Henri Gosselin
  • Fonction : Auteur
  • PersonId : 1135783
Christian Raymond
Yann Ricquebourg
Bertrand B. Coüasnon

Résumé

While the performance of face alignment models has been improving over the years, they still need large, annotated datasets during their training to perform well. In this paper, we propose a new architecture to perform face alignment with limited training data. Our model is based on StyleGAN, a popular architecture in the image generation domain, and takes advantage of its strong generative power to generate accurate facial landmark heatmaps of real face images, using only a small amount of training data. Even when trained down to only 50 samples, our model can still predict accurate facial landmarks. It exceeds state-of-the-art on several face alignment datasets in the low training data regime.
Fichier principal
Vignette du fichier
Publication ID1349_StyleGAN-based_heatmap_generator_for_face_alignment_with_limited_training_data (1).pdf (4.41 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03778322 , version 1 (16-09-2022)
hal-03778322 , version 2 (07-03-2023)

Identifiants

  • HAL Id : hal-03778322 , version 2

Citer

Martin Dornier, Philippe-Henri Gosselin, Christian Raymond, Yann Ricquebourg, Bertrand B. Coüasnon. StyleGAN-based heatmap generator for face alignment with limited training data. 2023. ⟨hal-03778322v2⟩
156 Consultations
286 Téléchargements

Partager

Gmail Facebook X LinkedIn More