RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion from the Perspective of Referring Image Segmentation
This addresses the challenge of aligning text guidance with fusion outcomes in multimodal image processing, offering a novel benchmark and method for domain-specific applications like surveillance or medical imaging.
The paper tackles the problem of text-driven infrared and visible image fusion by proposing RIS-FUSION, a cascaded framework that unifies fusion with referring image segmentation through joint optimization, achieving state-of-the-art performance with over 11% improvement in mIoU.
Text-driven infrared and visible image fusion has gained attention for enabling natural language to guide the fusion process. However, existing methods lack a goal-aligned task to supervise and evaluate how effectively the input text contributes to the fusion outcome. We observe that referring image segmentation (RIS) and text-driven fusion share a common objective: highlighting the object referred to by the text. Motivated by this, we propose RIS-FUSION, a cascaded framework that unifies fusion and RIS through joint optimization. At its core is the LangGatedFusion module, which injects textual features into the fusion backbone to enhance semantic alignment. To support multimodal referring image segmentation task, we introduce MM-RIS, a large-scale benchmark with 12.5k training and 3.5k testing triplets, each consisting of an infrared-visible image pair, a segmentation mask, and a referring expression. Extensive experiments show that RIS-FUSION achieves state-of-the-art performance, outperforming existing methods by over 11% in mIoU. Code and dataset will be released at https://github.com/SijuMa2003/RIS-FUSION.