.png){kind=icon}
返回
Variational Diffusion Method for Remote Sensing Image Fusion
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2024.3388167.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Image fusion (IF) aims to integrate valuable information from multiple sources, and the fusion of optical image and synthetic aperture radar (SAR) is at the core of remote sensing IF. Despite the remarkable capability of deep learning in IF, it often depends on costly datasets, lacks explicit interpretability, and has an instable training process. Diffusion models (DMs), such as diffusion denoising probabilistic model and its continuous form (i.e., score-based DM), exhibit powerful generative ability and offer novel ideas to address the hurdles above. To this end, it is kernel and challenge to robustly estimate the posterior distribution of ground truth with respect to given measurements. In this letter, we propose a variational diffusion IF method for robust estimation of posterior distribution. First, an optimization model is developed in the framework of variational inference, where the fidelity term comes from traditional optimization fusion model and the regularization term is actually a weighted integral form of the score function matching. Then, a fast numerical algorithm is designed via first-order stochastic optimization, significantly reducing computational complexity. Finally, the proposed method is validated in experiments with WHU-OPT-SAR and SEN1-2 real datasets, and the results show that the proposed method not only outperforms the state-of-the-art methods in terms of fused image quality but also almost has half of computational complexity of existing DM IF methods.
Keyword:
Diffusion denoising probabilistic model
image fusion (IF)
posterior distribution
variational inference
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
分享收藏Biodegradable Poly(d,l-lactide-co-ε-caprolactone) Electrospun Scaffolds Outperform Antifibrotic-Loaded Meshes in an in Vivo Tissue Regeneration Model可生物降解的聚(D,L-丙交酯-co-ε-己内酯)电纺支架在体内组织再生模型中优于抗纤维化负载的网片
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion ModelsDif融合: 在具有扩散模型的红外和可见光图像融合中实现高色彩保真度
PREAI
分享收藏Parenting Education in Indonesia: Review and Recommendations to Strengthen Programs and Systems.png)
OAAI
IF0
OAAI分享收藏Combining the spectral PCA and spatial PCA fusion methods by an optimal filterINFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏
查看更多内容