Controlling Neural Style Transfer with Deep Reinforcement Learning

Chengming Feng, Jing Hu, Xin Wang, Shu Hu, Bin Zhu, Xi Wu, Hongtu Zhu, Siwei Lyu

IJCAI 2023 pp. 100-108

doi:10.24963/IJCAI.2023/12 /ijcai/2023/feng2023ijcai-controlling/

Abstract

Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters. In this paper, we propose the first deep Reinforcement Learning (RL) based architecture that splits one-step style transfer into a step-wise process for the NST task. Our RL-based method tends to preserve more details and structures of the content image in early steps, and synthesize more style patterns in later steps. It is a user-easily-controlled style-transfer method. Additionally, as our RL-based model performs the stylization progressively, it is lightweight and has lower computational complexity than existing one-step Deep Learning (DL) based models. Experimental results demonstrate the effectiveness and robustness of our method.

PDF IJCAI Semantic Scholar

Cite

Text

Feng et al. "Controlling Neural Style Transfer with Deep Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/12

Markdown

[Feng et al. "Controlling Neural Style Transfer with Deep Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/feng2023ijcai-controlling/) doi:10.24963/IJCAI.2023/12

BibTeX

@inproceedings{feng2023ijcai-controlling,
  title     = {{Controlling Neural Style Transfer with Deep Reinforcement Learning}},
  author    = {Feng, Chengming and Hu, Jing and Wang, Xin and Hu, Shu and Zhu, Bin and Wu, Xi and Zhu, Hongtu and Lyu, Siwei},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {100-108},
  doi       = {10.24963/IJCAI.2023/12},
  url       = {https://mlanthology.org/ijcai/2023/feng2023ijcai-controlling/}
}