Parameter-Free Style Projection for Arbitrary Style Transfer
Abstract
Arbitrary image style transfer is a challenging task which aims to stylize a content image conditioned on arbitrary style images. In this task the feature-level content-style transformation plays a vital role for proper fusion of features. Existing feature transformation algorithms often suffer from loss of content or style details, non-natural stroke patterns, and unstable training. To mitigate these issues, this paper proposes a new feature-level style transformation technique, named Style Projection, for parameter-free, fast, and effective content-style transformation. This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs. Extensive qualitative analysis, quantitative evaluation, and user study have demonstrated the effectiveness and efficiency of the proposed methods.
Cite
@article{arxiv.2003.07694,
title = {Parameter-Free Style Projection for Arbitrary Style Transfer},
author = {Siyu Huang and Haoyi Xiong and Tianyang Wang and Bihan Wen and Qingzhong Wang and Zeyu Chen and Jun Huan and Dejing Dou},
journal= {arXiv preprint arXiv:2003.07694},
year = {2022}
}
Comments
ICASSP 2022. Project page https://www.paddlepaddle.org.cn/hubdetail?name=stylepro_artistic and Code https://github.com/PaddlePaddle/PaddleHub/tree/dbca09ae78b5387ebe3b49f37ce88de45d41d26a/hub_module/modules/image/style_transfer/stylepro_artistic