Decomposed and DPP-Guided Paradigm for Infrared and Visible Video Fusion

Infrared and Visible Video Fusion (IVVF) integrates complementary information from heterogeneous sensors to produce informative and temporally coherent videos. However, existing methods suffer from spatio-temporal optimization imbalances, yielding motion ghosting or temporal incoherence, while inadequate cross-modal exploitation causes spatial misalignment. To address these issues, we propose $D^2$Fusion, a Decomposed and Determinantal Point Process (DPP)-guided fusion network. With better prior understanding provided by large-scale visual models, $D^2$Fusion enhances spatio-temporal consistency, leveraging them to modulate global motion and refine local details. Moreover, the opposing constraints between temporal consistency and spatial richness are abstracted as a quality–diversity trade-off unified under a DPP objective to balance them. Beyond intra-modal priors, we enforce a modality-invariant prior over shared geometric structures against cross-modal misalignment, preserving modality-specific cues. Extensive experiments on M3SVD establish $D^2$Fusion as SOTA with strong cross-dataset generalization.