Image style transfer aims to integrate the visual patterns of a specific artistic style into a content image while preserving its content structure. Existing methods mainly rely on the generative adversarial network (GAN) or stable diffusion (SD). GAN-based approaches using CNNs or Transformers struggle to jointly capture local and global dependencies, leading to artifacts and disharmonious patterns. SD-based methods reduce such issues but often fail to preserve content structures and suffer from slow inference. To address these issues, we revisit GAN and propose a mamba-based generator, termed as StyMam, to produce high-quality stylized images without introducing artifacts and disharmonious patterns. Specifically, we introduce a mamba-based generator with a residual dual-path strip scanning mechanism and a channel-reweighted spatial attention module. The former efficiently captures local texture features, while the latter models global dependencies. Finally, extensive qualitative and quantitative experiments demonstrate that the proposed method outperforms state-of-the-art algorithms in both quality and speed.
@article{arxiv.2601.12954,
title = {StyMam: A Mamba-Based Generator for Artistic Style Transfer},
author = {Zhou Hong and Ning Dong and Yicheng Di and Xiaolong Xu and Rongsheng Hu and Yihua Shao and Run Ling and Yun Wang and Juqin Wang and Zhanjie Zhang and Ao Ma},
journal= {arXiv preprint arXiv:2601.12954},
year = {2026}
}