Preprint
Aug 2026
Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations
TGFusion is proposed, a text-guided latent-space flow matching framework that unifies degradation suppression and cross-modal fusion and achieves superior or competitive performance in perceptual quality, image naturalness, structural-detail preservation, and infrared-saliency retention, while remaining robust across diverse single and compound degradations.
Axi Niu, Jiehua Li, Kang Zhang et al.
· 0 citations