A general image fusion framework using multi-task semi-supervised learning

Wu Wang, Liang-Jian Deng, Gemine Vivone

Abstract: Highlights•Our method can solve several image fusion problems with a single model.•We propose a multi-task semi-supervised training method to extract complementary information from different tasks.•We propose the PSLPT, which decomposes the source images into features of different frequencies and adaptively learns to merge these features.