An Improved Image Transformation Network for Neural Style Transfer - Intelligence Science I (ICIS 2017) Access content directly
Conference Papers Year : 2017

An Improved Image Transformation Network for Neural Style Transfer

Hong-Xu Qiu
  • Function : Author
  • PersonId : 1033388
Xiao-Xia Huang
  • Function : Author
  • PersonId : 1033389

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Licence

Attribution

Identifiers

Cite

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 View
106 Download

Altmetric

Share

Gmail Facebook X LinkedIn More