DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912300930170880 |
|---|---|
| author | Tang, Linfeng Li, Chunyu Wang, Guoqing Yuan, Yixuan Ma, Jiayi |
| author_facet | Tang, Linfeng Li, Chunyu Wang, Guoqing Yuan, Yixuan Ma, Jiayi |
| contents | Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and \textbf{S}emantic \textbf{P}rior dual-guided framework for degraded image \textbf{Fusion} (\textbf{DSPFusion}), utilizing degradation priors and high-quality scene semantic priors restored via diffusion models to guide both information recovery and fusion in a unified model. In specific, it first individually extracts modality-specific degradation priors, while jointly capturing comprehensive low-quality semantic priors. Subsequently, a diffusion model is developed to iteratively restore high-quality semantic priors in a compact latent space, enabling our method to be over $20 \times$ faster than mainstream diffusion model-based image fusion schemes. Finally, the degradation priors and high-quality semantic priors are employed to guide information enhancement and aggregation via the dual-prior guidance and prior-guided fusion modules. Extensive experiments demonstrate that DSPFusion mitigates most typical degradations while integrating complementary context with minimal computational cost, greatly broadening the application scope of image fusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance Tang, Linfeng Li, Chunyu Wang, Guoqing Yuan, Yixuan Ma, Jiayi Computer Vision and Pattern Recognition Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and \textbf{S}emantic \textbf{P}rior dual-guided framework for degraded image \textbf{Fusion} (\textbf{DSPFusion}), utilizing degradation priors and high-quality scene semantic priors restored via diffusion models to guide both information recovery and fusion in a unified model. In specific, it first individually extracts modality-specific degradation priors, while jointly capturing comprehensive low-quality semantic priors. Subsequently, a diffusion model is developed to iteratively restore high-quality semantic priors in a compact latent space, enabling our method to be over $20 \times$ faster than mainstream diffusion model-based image fusion schemes. Finally, the degradation priors and high-quality semantic priors are employed to guide information enhancement and aggregation via the dual-prior guidance and prior-guided fusion modules. Extensive experiments demonstrate that DSPFusion mitigates most typical degradations while integrating complementary context with minimal computational cost, greatly broadening the application scope of image fusion. |
| title | DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23355 |