TextFusion: Unveiling the power of textual semantics for controllable image fusion

Chunyang Cheng, Tianyang Xu, Xiaojun Wu, Hui Li, Xi Li, Zhangyong Tang, Josef Kittler

Abstract: Highlights•Text semantics enhance the control of image fusion outcomes.•Textual data is utlised for improved image fusion quality and analysis.•The proposed method achieves distinct advantages in evaluations.•Refined metrics are introduced for more accurate image fusion assessments.•A dataset with text annotations is created for advancing related research.