arXiv 2601.129542026-01-25cs.CV

StyMam：基于Mamba的风格迁移生成器

StyMam: A Mamba-Based Generator for Artistic Style Transfer

School of Information Engineering, Suqian University（信息工程学院，苏庆大学）；School of Artificial Intelligence and Computer Science, Jiangnan University（人工智能与计算机科学学院，江南大学）；Jiangsu Province Engineering Research Center of Smart Poultry Farming and Intelligent Equipment（江苏省智能养鸡场与智能设备工程研究中心）；School of Computer Science, Nanjing University of Posts and Telecommunications（计算机科学学院，南京邮电大学）；Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）；School of Internet of Things, Wuxi University of Technology（物联网学院，无锡科技大学）

Zhou Hong, Ning Dong, Yicheng Di, Xiaolong Xu, Rongsheng Hu, Yihua Shao, Run Ling, Yun Wang, Juqin Wang, Zhanjie Zhang, Ao Ma

备注：: Accepted by ICASSP 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

StyMam通过引入基于Mamba的生成器，结合残差双路径扫描机制和通道加权空间注意力模块，实现了高质量且快速的图像风格迁移。

摘要：

图像风格迁移旨在将特定艺术风格的视觉模式整合到内容图像中，同时保持其内容结构。现有方法主要依赖生成对抗网络（GAN）或稳定扩散（SD）。基于CNN或Transformer的GAN方法难以同时捕捉局部和全局依赖关系，导致伪影和不和谐的模式。基于SD的方法减少了这些问题，但往往无法保持内容结构，并且推理速度慢。为了解决这些问题，我们重新审视GAN并提出一种基于Mamba的生成器，称为StyMam，以生成高质量的风格化图像，而无需引入伪影和不和谐的模式。具体而言，我们引入了一种基于Mamba的生成器，其包含残差双路径 strip 扫描机制和通道加权空间注意力模块。前者高效地捕捉局部纹理特征，后者建模全局依赖关系。最后，广泛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最先进的算法。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。