.png){kind=icon}
.png){kind=icon}
Return
MinT: Multi-scale implicit neural transformer for image deraining
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2026.08.022.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• MinT formulates deraining as cross-scale representation learning.
• Scale-specific Transformer branches model scale-varying rain.
• INR bridges enable continuous cross-scale representation.
• AFFM promotes reliable bidirectional inter-scale fusion.
• MinT achieves competitive results on five deraining benchmarks.
Keywords:
Deraining
Image restoration
Transformer
Implicit representation
Multiscale learning
Journal
IF:
3.3
Papers:
7.9K
Citations:
1.6W
Organization
View more organizations