A Low Rank Gaussian Mixture Latent Model for Face Generation - GREYC image
Communication Dans Un Congrès Année : 2024

A Low Rank Gaussian Mixture Latent Model for Face Generation

Résumé

Generative modeling of natural images has seen significant progress, but large-scale foundation models raise concerns about environmental impact, privacy, and biases. This motivates investigating more efficient and interpretable generative models. This work proposes a simple latent parametric generative model focused on realistic face generation, a domain that has seen success with neural networks. The model uses a low-dimensional latent representation from a pre-trained autoencoder, and proceeds in two stages: (1) modeling the latent distribution as a mixture of multivariate Gaussians trained on a limited dataset, and (2) generating low-rank random codes from this prior and remapping them using nearest neighbor matching. Comparative experiments demonstrate the advantages of the proposed approach.
Fichier principal
Vignette du fichier
output.pdf (3.58 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04715052 , version 1 (30-09-2024)

Identifiants

  • HAL Id : hal-04715052 , version 1

Citer

Benjamin Samuth, Julien Rabin, Frédéric Jurie, David Tschumperlé. A Low Rank Gaussian Mixture Latent Model for Face Generation. International Conference on Pattern Recognition, Dec 2024, Kolkata, India. ⟨hal-04715052⟩
0 Consultations
0 Téléchargements

Partager

More