TPTAF: Task-Prior Tripartite Attention for Infrared and Visible Image Fusion

Infrared and visible image fusion aims to integrate complementary information to produce informative fused images for visual perception and downstream tasks. However, mainstream methods often focus on fusion reconstruction, while losses from different tasks may introduce competing optimization demands, making it difficult to balance visual quality and detection performance. To address this issue, we propose task-prior tripartite attention for infrared and visible image fusion (TPTAF), which introduces detection semantics as task-prior guidance for representation-level cross-modal interaction. TPTAF employs a decoupled encoder to organize infrared and visible features into structural and discriminative spaces, enabling cross-modal layout consistency and modality-specific detail preservation to be modeled with different roles. Meanwhile, detection semantics extracted from hybrid infrared-visible features are transformed into task priors and integrated with the decoupled representations through tripartite attention. In this interaction, structural cues stabilize the fusion layout, while task-prior guidance regulates the selection of discriminative details toward target-related evidence. For joint optimization, uncertainty-weighted learning further balances fusion and detection losses, reducing the dependence on manually assigned loss weights. Experiments on M3FD, RoadScene, AVMS, and MSRS demonstrate that TPTAF maintains stable fusion quality across different data distributions while improving the utility of fused images for downstream object detection and semantic segmentation evaluation. The code will be made available at https://github.com/Duxeno/TPTAF.