Fig. 1. Overall network framework

Fig. 2. Multi-scale feature extraction diagram

Fig. 3. Dense connected module

Fig. 4. Convolutional block attention module

Fig. 5. Deformable Convolution

Fig. 6. Comparison of standard convolution and deformable convolution

Fig. 7. Channel attention module

Fig. 8. Spatial Attention Module

Fig. 9. Fusion strategy based on L1 norm

Fig. 10. Encoder subnet structure

Fig. 11. Comparison of fusion results of “street”

Fig. 12. Results of infrared and visible image fusion based on TNO dataset with different algorithms

Fig. 13. Comparison of six objective metrics for different algorithms

Fig. 14. Results of ablation experiments