SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.
Refusion: Learning image fusion from reconstruction with learnable loss via meta-learning.International Journal of Com- puter Vision, pages 1–21,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images
SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.