A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Proceedings of the 20th ACM SIGGRAPH European Conference on Visual Media Production Année : 2023

A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing

Espace latent compact et sémantique pour l'édition désenchevêtrée d'images

Résumé

Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their powerful ability to apply realistic modifications to an image, these methods often lack properties like disentanglement (the capacity to edit attributes independently). In this paper, we propose an auto-encoder which reorganizes the latent space of StyleGAN, so that each attribute which we wish to edit corresponds to an axis of the new latent space, and furthermore that the latent axes are decorrelated, encouraging disentanglement. We work in a compressed version of the latent space, using Principal Component Analysis, meaning that the parameter complexity of our autoencoder is reduced, leading to short training times (∼ 45 mins). Qualitative and quantitative results demonstrate the editing capabilities of our approach, with greater disentanglement than competing methods, while maintaining fidelity to the original image with respect to identity. Our autoencoder architecture simple and straightforward, facilitating implementation.
Fichier principal
Vignette du fichier
Disentangler_preprint (1).pdf (38.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04343073 , version 1 (13-12-2023)

Identifiants

Citer

Gwilherm Lesné, Yann Gousseau, Saïd Ladjal, Alasdair Newson. A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing. CVMP '23: European Conference on Visual Media Production, Proceedings of the 20th ACM SIGGRAPH European Conference on Visual Media Production, ACM, pp.1-10, 2023, ⟨10.1145/3626495.3626508⟩. ⟨hal-04343073⟩
36 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More