融合
不透明度
扩散
计算机科学
红外线的
人工智能
图像融合
计算机视觉
模式识别(心理学)
骨料(复合)
传感器融合
降噪
代表(政治)
图像(数学)
编码(集合论)
图像处理
源代码
算法
作者
Maoyi Xiong,Junjie Huang,Zihan Chen,Tianrui Liu,Xueqiong Li,Lin Liu,Wentao Zhao,Yuhua Tang
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-06-30
卷期号:: 1-6
被引量:2
标识
DOI:10.1109/icme59968.2025.11210127
摘要
Infrared and Visible Image Fusion (IVF) intends to aggregate information from infrared and visible modalities, generating comprehensive images. While deep-unfolding-based methods and diffusion-based methods show satisfactory performances, the former suffers from insufficiently deterministic priors, and latter is limited by the inaccurate prior generation or opaque working mechanisms. In this paper, we propose Deep infrared and visible image Fusion with Diffusion prior Unfolding Network (DFDUN), aiming for effective fusion with the generative diffusion prior in a transparent mechanism. DFDUN starts with a model-based fusion optimization formulation, which is unfolded into a Denoising Diffusion Module (DDM) for generating informative diffusion prior, and a Data Consistent Module (DCM) that transparently and effectively aggregates complementary information from diffusion prior and source modalities. Moreover, DFDUN employs a hypernetwork for adaptive dictionary parameter generation in DCM, enhancing fusion flexibility. Experimental results indicate that DFDUN outperforms existing methods, providing superior IVF performance with efficient and transparent fusion. Code is available at https://github.com/XiongMaoyi2001/DFDUN.
科研通智能强力驱动
Strongly Powered by AbleSci AI