Dig2DIG: Dig into Diffusion Information Gains for Image Fusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908281042108416 |
|---|---|
| author | Cao, Bing Cai, Baoshuo Zhang, Changqing Hu, Qinghua |
| author_facet | Cao, Bing Cai, Baoshuo Zhang, Changqing Hu, Qinghua |
| contents | Image fusion integrates complementary information from multi-source images to generate more informative results. Recently, the diffusion model, which demonstrates unprecedented generative potential, has been explored in image fusion. However, these approaches typically incorporate predefined multimodal guidance into diffusion, failing to capture the dynamically changing significance of each modality, while lacking theoretical guarantees. To address this issue, we reveal a significant spatio-temporal imbalance in image denoising; specifically, the diffusion model produces dynamic information gains in different image regions with denoising steps. Based on this observation, we Dig into the Diffusion Information Gains (Dig2DIG) and theoretically derive a diffusion-based dynamic image fusion framework that provably reduces the upper bound of the generalization error. Accordingly, we introduce diffusion information gains (DIG) to quantify the information contribution of each modality at different denoising steps, thereby providing dynamic guidance during the fusion process. Extensive experiments on multiple fusion scenarios confirm that our method outperforms existing diffusion-based approaches in terms of both fusion quality and inference efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18627 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dig2DIG: Dig into Diffusion Information Gains for Image Fusion Cao, Bing Cai, Baoshuo Zhang, Changqing Hu, Qinghua Computer Vision and Pattern Recognition Artificial Intelligence Image fusion integrates complementary information from multi-source images to generate more informative results. Recently, the diffusion model, which demonstrates unprecedented generative potential, has been explored in image fusion. However, these approaches typically incorporate predefined multimodal guidance into diffusion, failing to capture the dynamically changing significance of each modality, while lacking theoretical guarantees. To address this issue, we reveal a significant spatio-temporal imbalance in image denoising; specifically, the diffusion model produces dynamic information gains in different image regions with denoising steps. Based on this observation, we Dig into the Diffusion Information Gains (Dig2DIG) and theoretically derive a diffusion-based dynamic image fusion framework that provably reduces the upper bound of the generalization error. Accordingly, we introduce diffusion information gains (DIG) to quantify the information contribution of each modality at different denoising steps, thereby providing dynamic guidance during the fusion process. Extensive experiments on multiple fusion scenarios confirm that our method outperforms existing diffusion-based approaches in terms of both fusion quality and inference efficiency. |
| title | Dig2DIG: Dig into Diffusion Information Gains for Image Fusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.18627 |