CS2Fusion: Contrastive learning for Self-Supervised infrared and visible image fusion by estimating feature compensation map

Open Webpage

Xue Wang, Zheng Guan, Wenhua Qian, Jinde Cao, Shu Liang, Jin Yan

Published: 01 Jan 2024, Last Modified: 17 Apr 2025Inf. Fusion 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A self-supervised-based infrared and visible image fusion method is proposed.•Mining complementary features based on identity and divergence of source features.•Improving information flow between layers by demand-driven module.•Our method can better facilitate high-level vision tasks than SOTA methods.