RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion From The Perspective of Referring Image Segmentation
Published in ICASSP, 2026
RIS-FUSION reframes text-driven infrared-visible fusion through referring image segmentation, connecting language guidance with interpretable fusion behavior and downstream task alignment.
Recommended citation: Siju Ma, Changxiyu Gong, Xiaofeng Fan, Yong Ma, and Chengjie Jiang. RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion From The Perspective of Referring Image Segmentation. ICASSP, 2026.
Download Paper
