DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912644939644928 |
|---|---|
| author | Zhang, Tianpei Zhao, Jufeng Zhu, Yiming Cui, Guangmang Jing, Yuxin |
| author_facet | Zhang, Tianpei Zhao, Jufeng Zhu, Yiming Cui, Guangmang Jing, Yuxin |
| contents | Conventional infrared and visible image fusion(IVIF) methods often assume high-quality inputs, neglecting real-world degradations such as low-light and noise, which limits their practical applicability. To address this, we propose a Degradation-Decoupled Fusion(DDFusion) framework, which achieves degradation decoupling and jointly models degradation suppression and image fusion in a unified manner. Specifically, the Degradation-Decoupled Optimization Network(DDON) performs degradation-specific decomposition to decouple inter-degradation and degradation-information components, followed by component-specific extraction paths for effective suppression of degradation and enhancement of informative features. The Interactive Local-Global Fusion Network (ILGFN) aggregates complementary features across multi-scale pathways and alleviates performance degradation caused by the decoupling between degradation optimization and image fusion. Extensive experiments demonstrate that DDFusion achieves superior fusion performance under both clean and degraded conditions. Our code is available at https://github.com/Lmmh058/DDFusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10871 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion Zhang, Tianpei Zhao, Jufeng Zhu, Yiming Cui, Guangmang Jing, Yuxin Computer Vision and Pattern Recognition Conventional infrared and visible image fusion(IVIF) methods often assume high-quality inputs, neglecting real-world degradations such as low-light and noise, which limits their practical applicability. To address this, we propose a Degradation-Decoupled Fusion(DDFusion) framework, which achieves degradation decoupling and jointly models degradation suppression and image fusion in a unified manner. Specifically, the Degradation-Decoupled Optimization Network(DDON) performs degradation-specific decomposition to decouple inter-degradation and degradation-information components, followed by component-specific extraction paths for effective suppression of degradation and enhancement of informative features. The Interactive Local-Global Fusion Network (ILGFN) aggregates complementary features across multi-scale pathways and alleviates performance degradation caused by the decoupling between degradation optimization and image fusion. Extensive experiments demonstrate that DDFusion achieves superior fusion performance under both clean and degraded conditions. Our code is available at https://github.com/Lmmh058/DDFusion. |
| title | DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10871 |