SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910886104399872 |
|---|---|
| author | Liu, Hongda Wang, Longguang Zhang, Ye Yu, Ziru Guo, Yulan |
| author_facet | Liu, Hongda Wang, Longguang Zhang, Ye Yu, Ziru Guo, Yulan |
| contents | Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global receptive fields. Recently, the State Space Model (SSM), especially the improved variant Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a approach to resolve the above dilemma. In this paper, we develop a Mamba-based style transfer framework, termed SaMam. Specifically, a mamba encoder is designed to efficiently extract content and style information. In addition, a style-aware mamba decoder is developed to flexibly adapt to various styles. Moreover, to address the problems of local pixel forgetting, channel redundancy and spatial discontinuity of existing SSMs, we introduce both local enhancement and zigzag scan. Qualitative and quantitative results demonstrate that our SaMam outperforms state-of-the-art methods in terms of both accuracy and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15934 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer Liu, Hongda Wang, Longguang Zhang, Ye Yu, Ziru Guo, Yulan Computer Vision and Pattern Recognition Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global receptive fields. Recently, the State Space Model (SSM), especially the improved variant Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a approach to resolve the above dilemma. In this paper, we develop a Mamba-based style transfer framework, termed SaMam. Specifically, a mamba encoder is designed to efficiently extract content and style information. In addition, a style-aware mamba decoder is developed to flexibly adapt to various styles. Moreover, to address the problems of local pixel forgetting, channel redundancy and spatial discontinuity of existing SSMs, we introduce both local enhancement and zigzag scan. Qualitative and quantitative results demonstrate that our SaMam outperforms state-of-the-art methods in terms of both accuracy and efficiency. |
| title | SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15934 |