融合
计算机科学
人工智能
图像融合
解耦(概率)
过程(计算)
模式识别(心理学)
降级(电信)
复合数
特征(语言学)
对角线的
图像(数学)
复合图像滤波器
融合机制
稳健性(进化)
编码(集合论)
计算机视觉
独立性(概率论)
编码(内存)
传感器融合
融合规则
特征提取
人工神经网络
棱锥(几何)
联轴节(管道)
源代码
代表(政治)
作者
Xuan Li,Zhaoming Feng,Xiang Yuan,Huabing Zhou,Jiayi Ma
标识
DOI:10.24963/ijcai.2026/155
摘要
Existing degradation-resistant infrared-visible image fusion methods struggle to effectively handle composite degradations, where multiple degradation types exhibit intricate coupling and mutual interference. To address this challenge, we propose SpeciFuse, an infrared-visible image fusion network that learns degradation-specific representations. By explicitly modeling the specificity of individual degradations through a siamese architecture trained on single-degradation data, our method effectively addresses the conflicts arising from multiple degradations, thereby achieving robust fusion performance that generalizes to diverse composite degradation scenarios. In SpeciFuse, a degradation-type specificity decoupling module is designed to disentangle the feature representations by attenuating their redundant correlations in a latent space. It minimizes off-diagonal elements to enforce independence among the encodings of distinct degradation types, while preserving dominant diagonal elements to maintain shared content information. Furthermore, a degradation-aware gated fusion module leverages these decoupled features to dynamically modulate cross-modal fusion across both channel and spatial dimensions. This facilitates a degradation-conditional fusion process that adaptively suppresses degradation artifacts while preserving beneficial information across varying conditions. In extensive comparisons with state-of-the-art methods, SpeciFuse demonstrates more robust performance under diverse composite degradations. The code is available at https://github.com/xbsj-cool/SpeciFuse.
科研通智能强力驱动
Strongly Powered by AbleSci AI