.png){kind=icon}
.png){kind=icon}
Return
Hierarchical gradient modulation for multi-resolution image registration
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112525.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• An unsupervised adaptive tuning algorithm is proposed to perform multi-resolution image registration by constructing hierarchical representations from high-resolution images. • A gradient modulation compatibility criterion is proposed to solve the gradient conflict problem of similarity loss and regularization loss. • By designing loss balance algorithms for multi-resolution structures, the generalization ability of the model is improved on multiple datasets.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W