ML Anthology

Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs

Thomas Irmer, Tobias Glasmachers, Subhransu Maji
WACV 2017 pp. 852-861
doi:10.1109/WACV.2017.100 /wacv/2017/irmer2017wacv-texture/

Abstract

We present a novel technique for texture synthesis and style transfer based on convolutional neural networks (CNNs). Our method learns feed-forward image generators that correspond to specification of styles and textures in terms of high-level describable attributes such as 'striped', 'dotted', or 'veined'. Two key conceptual advantages over template-based approaches are that attributes can be analyzed and activated individually, while a template image necessarily represents a simultaneous specification of many attributes, and that attributes can combine aspects of many texture templates allowing flexibility in the generation process. Once the attribute-wise networks are trained, applications to texture synthesis and style transfer are fast, allowing for real-time video processing.

WACV Semantic Scholar

Cite

Text

Irmer et al. "Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017. doi:10.1109/WACV.2017.100

Markdown

[Irmer et al. "Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017.](https://mlanthology.org/wacv/2017/irmer2017wacv-texture/) doi:10.1109/WACV.2017.100

BibTeX

@inproceedings{irmer2017wacv-texture,
  title     = {{Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs}},
  author    = {Irmer, Thomas and Glasmachers, Tobias and Maji, Subhransu},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2017},
  pages     = {852-861},
  doi       = {10.1109/WACV.2017.100},
  url       = {https://mlanthology.org/wacv/2017/irmer2017wacv-texture/}
}