LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing

Benjamin Samuth (1, 2, 3) , Julien Rabin (3, 2, 1) , David Tschumperlé (3, 2, 1) , Frédéric Jurie (3, 2, 1)

1 UNICAEN - Université de Caen Normandie
2 ENSICAEN - École Nationale Supérieure d'Ingénieurs de Caen
3 Equipe Image - Laboratoire GREYC - UMR6072

This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. We use a lightweight model with only a few thousand parameters. Unlike traditional few-shot generation methods that finetune pre-trained large-scale generative models, our approach is computed directly on the latent distribution by sequential feature matching, and is explainable by design. Avoiding large models based on transformers, recursive networks, or self-attention, which are not suitable for small datasets, our method is inspired by non-parametric texture synthesis and style transfer models, and ensures that generated image features are sampled from the source distribution. We extend previous single-image models to work with a few images and demonstrate that our method can generate realistic images, as well as enable conditional sampling and image editing. We conduct experiments on face datasets and show that our simplistic model is effective and versatile.

Mots clés: Face Generation Generative model Autoencoder Latent representation Image edition; Face Generation; Generative model; Autoencoder; Latent representation; Image edition; Patch-based Method

Domaines: Traitement des images [eess.IV]; Multimédia [cs.MM]; Traitement du signal et de l'image [eess.SP]

Benjamin Samuth, Julien Rabin, David Tschumperlé, Frédéric Jurie. LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing. 2023 IEEE International Conference on Image Processing (ICIP), Oct 2023, Kuala Lumpur, Malaysia. pp.1790-1794, ⟨10.1109/ICIP49359.2023.10222005⟩. ⟨hal-04411751⟩