A Degradation-Resistant Unfolding Network (DeRUN) for HIF (Heterogeneous image fusion) is a concept that unifies the interpretability of model-based methods and the generalizability of deep learning-based solutions. Extensive experiments have shown that DeRUN significantly outperforms existing methods on four HIF tasks as well as downstream applications using cheaper computational and memory costs.


Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion

Heterogeneous image fusion (HIF) aims to enhance image quality by merging complementary information of images captured by different sensors. Early model-based approaches have strong interpretability while being limited by non-adaptive feature extractors with poor generalizability.