An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909960708816896 |
|---|---|
| author | Li, Shaoxu Pan, Ye |
| author_facet | Li, Shaoxu Pan, Ye |
| contents | Despite significant advancements in image generation using advanced generative frameworks, cross-image integration of content and style remains a key challenge. Current generative models, while powerful, frequently depend on vague textual prompts to define styles--creating difficulties in balancing content semantics and style preservation. We propose a novel framework that utilizes customized models to learn style representations. It enhances content preservation through cross-model feature and attention modulation, leveraging the inherent semantic consistency across models. Additionally, we introduce fixed feature and adaptive attention fusion to achieve the desired balance between content and style. We further develop spatial (mask-guided localized) and temporal (multi-style compositional) multi-model combinations, enabling flexible fusion of models and styles. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in balancing content preservation and stylistic coherence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18461 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration Li, Shaoxu Pan, Ye Computer Vision and Pattern Recognition Despite significant advancements in image generation using advanced generative frameworks, cross-image integration of content and style remains a key challenge. Current generative models, while powerful, frequently depend on vague textual prompts to define styles--creating difficulties in balancing content semantics and style preservation. We propose a novel framework that utilizes customized models to learn style representations. It enhances content preservation through cross-model feature and attention modulation, leveraging the inherent semantic consistency across models. Additionally, we introduce fixed feature and adaptive attention fusion to achieve the desired balance between content and style. We further develop spatial (mask-guided localized) and temporal (multi-style compositional) multi-model combinations, enabling flexible fusion of models and styles. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in balancing content preservation and stylistic coherence. |
| title | An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18461 |