.png){kind=icon}
.png){kind=icon}
Return
Retrieval-augmented image harmonization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112556.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• The proposed Raiha guides image harmonization by retrieving an external reference. • A retrieval strategy is delicately designed to provide reliable references. • Semantic-guided fusion suppresses the influence of irrelevant regions. • A data augmentation strategy ensures Raiha utilize references effectively. • The proposed method outperforms the SOTAs on the image harmonization task.
Keywords:
Image enhancement
Image harmonization
Image retrieval
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W