.png){kind=icon}
.png){kind=icon}
Return
Region-aware diverse image stylization: enhancing fidelity and diversity through object-background augmentation
.png){kind=icon}
PRE
AI
Y
Y
W
J
B
Z
W
DOI：10.1007/s00371-026-04516-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Diverse stylization
Region-aware pattern aggregation attention
Object-background augmented attention
Color histogram-based contrastive loss
Journal
IF:
2.9
Papers:
4.5K
Citations:
6.5K
Organization
Cited Papers