A Patch-Based Algorithm for Diverse and High Fidelity Single Image Generation - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A Patch-Based Algorithm for Diverse and High Fidelity Single Image Generation

Résumé

Image generation is the task of producing new samples from one or several example images. Until recently, this has been done using large image databases, in particular using Generative Adversarial Networks (GANs). However, Shaham et al. [1] recently proposed the SinGAN method, which achieves this generation using a single image example. At the same time, researchers are realizing that classical patchbased methods can replace certain neural networks, with no costly training. In this paper, we present a purely patch-based method, named Patches for Single image generation (PSin), which requires no training and generates samples in seconds. Our algorithm is based on the minimization of a global, patchbased energy functional, which ensures the visual fidelity of the result to the original image. We also ensure diversity of the results by carefully choosing the initialization of the algorithm. We propose two initialization variants. We compare our results to both the original SinGAN and another recent patch-based image generation approach, both qualitatively and quantitatively using multiple metrics.
Fichier principal
Vignette du fichier
_ICIP_2022__PSin.pdf (2.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03822204 , version 1 (20-10-2022)

Identifiants

  • HAL Id : hal-03822204 , version 1

Citer

Nicolas Cherel, Andrés Almansa, Yann Gousseau, Alasdair Newson. A Patch-Based Algorithm for Diverse and High Fidelity Single Image Generation. 29th IEEE International Conference on Image Processing (ICIP) 2022, Oct 2022, Bordeaux, France. ⟨hal-03822204⟩
157 Consultations
187 Téléchargements

Partager

Gmail Facebook X LinkedIn More