2 papers
cs.CV2025
FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching
Huayi Zhu, Xiu Shu, Youqiang Xiong +5
Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified…
cs.CV2024
Progressive Domain Adaptation for Thermal Infrared Object Tracking
Qiao Li, Kanlun Tan, Qiao Liu +3
Due to the lack of large-scale labeled Thermal InfraRed (TIR) training datasets, most existing TIR trackers are trained directly on RGB datasets. However, tracking methods trained…