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.
@article{arxiv.2310.00405,
title = {Controlling Neural Style Transfer with Deep Reinforcement Learning},
author = {Chengming Feng and Jing Hu and Xin Wang and Shu Hu and Bin Zhu and Xi Wu and Hongtu Zhu and Siwei Lyu},
journal= {arXiv preprint arXiv:2310.00405},
year = {2024}
}
Comments
Accepted by IJCAI 2023. The contributions of Chengming Feng and Jing Hu to this paper were equal. arXiv admin note: substantial text overlap with arXiv:2309.13672