FusionDN: A Unified Densely Connected Network for Image Fusion

By Han Xu, Jiayi Ma, Zhuliang Le, Junjun Jiang, Xiaojie Guo. AAAI Conference on Artificial Intelligence, 2020

601 citations recorded by the source corpus.

In this paper, we present a new unsupervised and unified densely connected network for different types of image fusion tasks, termed as FusionDN. In our method, the densely connected network is trained to generate the fused image conditioned on source images. Meanwhile, a weight block is applied to obtain two data-driven weights as the retention degrees of features in different source images, which are the measurement of the quality and the amount of information in them. Losses of similarities based on these weights are applied for unsupervised learning. In addition, we obtain a single model applicable to multiple fusion tasks by applying elastic weight consolidation to avoid forgetting what has been learned from previous tasks when training multiple tasks sequentially, rather than train individual models for every fusion task or jointly train tasks roughly. Qualitative and quantitative results demonstrate the advantages of FusionDN compared with state-of-the-art methods in different fusion tasks.

Subfields: Biomedical Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/fa847d523443e5f5e4791d5b0a1f78f9951b5d52

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Media Technology

Citations in the corpus

SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, background): “In addition, Xu et al. developed a uniﬁed model for multi-fusion missions, which can achieve cross-fertilization between different fusion tasks [42], [43].”
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (2022, methodology): “IVF experiments use three popular benchmarks to verify our fusion model, i.e., MSRS [57], RoadScene [71], and TNO [59].”
SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, background): “developed a unified unsupervised image fusion model for multi-fusion tasks by combining the learnable information measurement and elastic weight consolidation [10], [62].”
U2Fusion: A Unified Unsupervised Image Fusion Network (2020, methodology): “However, it causes some false edges, as in the results of FusionDN in the fourth and ﬁfth columns.”
Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “4) We have evaluated the proposed DNFusion on the TNO dataset [19], FLIR-test dataset [20], near-infrared (NIR) dataset [21], and multiscenario multimodality (M 3 FD) dataset [22].”
Visible and Infrared Image Fusion Using Deep Learning (2023, methodology): “Some VIF datasets, including TNO [176], INO [177], MFNet [178], RoadScene [61], VIFB [167], LLVIP [179] and M3FD [115], have been utilized in the VIF task as test sets to evaluate image fusion performance.”
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion (2023, methodology): “This technology provides a clearer representation of objects and scenes, and has diverse applica-∗ [51] and Road-Scene [59] in Tab.”