An Improved Image Transformation Network for Neural Style Transfer - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

An Improved Image Transformation Network for Neural Style Transfer

Hong-Xu Qiu
  • Fonction : Auteur
  • PersonId : 1033388
Xiao-Xia Huang
  • Fonction : Auteur
  • PersonId : 1033389

Résumé

By using Convolutional Neural Networks (CNNs), the semantics and styles of images can be separated and recombined to create fascinating images. In this paper, an image transformation network for style transfer is proposed, which consists of convolution layers, deconvolution layers and Fusion modules composed of two 1 × 1 convolution layers and a residual block. The output of each layer in the network is normalized using batch normalization to speed up the training process. Compared with other networks, our network has fewer parameters and better real-time performance while generating similar quality images.
Fichier principal
Vignette du fichier
978-3-319-68121-4_28_Chapter.pdf (465.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01820915 , version 1 (22-06-2018)

Licence

Paternité

Identifiants

Citer

Hong-Xu Qiu, Xiao-Xia Huang. An Improved Image Transformation Network for Neural Style Transfer. 2nd International Conference on Intelligence Science (ICIS), Oct 2017, Shanghai, China. pp.260-267, ⟨10.1007/978-3-319-68121-4_28⟩. ⟨hal-01820915⟩
155 Consultations
106 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More