• DOI:10.2312/exp.20191073
Corpus ID: 44062991

Learning from multi-domain artistic images for arbitrary style transfer

@article{Xu2019LearningFM,
  title={Learning from multi-domain artistic images for arbitrary style transfer},
  author={Zheng Xu and Michael J. Wilber and Chen Fang and Aaron Hertzmann and H. Jin},
  journal={Proceedings of the 8th ACM/Eurographics Expressive Symposium on Computational Aesthetics and Sketch Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering},
  year={2019}
}

Zheng Xu, Michael J. Wilber, +2 authors H. Jin

Published 2019

Computer Science

Proceedings of the 8th ACM/Eurographics Expressive Symposium on Computational Aesthetics and Sketch Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering

We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs. Besides the traditional content and style representation based on deep features and statistics for textures, we use adversarial networks to regularize the generation of stylized images. Our adversarial network learns the intrinsic property of image styles from large-scale multi-domain artistic images. The adversarial training is challenging… CONTINUE READING

View on ACM

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed