Mixture of Style Experts for Diverse Image Stylization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918413937410048 |
|---|---|
| author | Zhu, Shihao Ouyang, Ziheng Kang, Yijia Wang, Qilong Zhou, Mi Li, Bo Cheng, Ming-Ming Hou, Qibin |
| author_facet | Zhu, Shihao Ouyang, Ziheng Kang, Yijia Wang, Qilong Zhou, Mi Li, Bo Cheng, Ming-Ming Hou, Qibin |
| contents | Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16649 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mixture of Style Experts for Diverse Image Stylization Zhu, Shihao Ouyang, Ziheng Kang, Yijia Wang, Qilong Zhou, Mi Li, Bo Cheng, Ming-Ming Hou, Qibin Computer Vision and Pattern Recognition Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/. |
| title | Mixture of Style Experts for Diverse Image Stylization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16649 |