Abstract
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.
Abstract (translated)
图像风格转换的目标是将特定艺术风格的视觉模式整合到内容图像中，同时保留其结构。现有的方法主要依赖于生成对抗网络（GAN）或稳定扩散（SD）。基于GAN的方法使用CNN或Transformer时，在捕捉局部和全局依赖性方面存在困难，导致出现伪影和不和谐图案。基于SD的方法减少了这些问题，但往往无法保存内容结构，并且在推理速度上较慢。 为了应对这些问题，我们重新审视了GAN技术，并提出了一种名为StyMam的基于蟒蛇（mamba）生成器的方法，以产生高质量、无伪影和不和谐图案的风格化图像。具体而言，我们引入了一个带有残差双路径条带扫描机制以及通道重权空间注意模块的基于蟒蛇的生成器。前者能够高效地捕捉局部纹理特征，而后者则用于建模全局依赖性。 最终，大量的定性和定量实验表明，所提出的方法在质量和速度方面均优于现有的先进算法。
URL
https://arxiv.org/abs/2601.12954
