Scholarlink

<p>Image style transfer is an important area of research, but existing methods often struggle to maintain content fidelity and produce diverse results. We propose region-aware diverse stylization (RDS) to address these limitations. Our method introduces two key components: an object-background augmented attention unit to improve structural detail, and an efficient pattern aggregation attention unit to capture dominant style features. We also design a color histogram-based contrastive loss to better align color distribution. Furthermore, we present the region-aware diverse stylization unit (RDSU), which generates multiple distinct stylized images from a single-style image without additional training. This enhances the method’s versatility and robustness. We also created a new high-quality dataset of 1000 images to support fine-grained structural learning. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in both fidelity and diversity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Region-aware diverse image stylization: enhancing fidelity and diversity through object-background augmentation

  • 期刊论文

  • 发表日期：

    2026年7月27日

查看全文
  • Yang Wen,
  • Yuhang Zhuang,
  • Wuzhen Shi,
  • Junyu Shi,
  • Bo Qian,
  • Zhiquan He,
  • Wenming Cao

摘要

Image style transfer is an important area of research, but existing methods often struggle to maintain content fidelity and produce diverse results. We propose region-aware diverse stylization (RDS) to address these limitations. Our method introduces two key components: an object-background augmented attention unit to improve structural detail, and an efficient pattern aggregation attention unit to capture dominant style features. We also design a color histogram-based contrastive loss to better align color distribution. Furthermore, we present the region-aware diverse stylization unit (RDSU), which generates multiple distinct stylized images from a single-style image without additional training. This enhances the method’s versatility and robustness. We also created a new high-quality dataset of 1000 images to support fine-grained structural learning. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in both fidelity and diversity.