SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness

doi:10.1109/JAS.2022.106082

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness
	Linfeng Tang; Yuxin Deng; Yong Ma; Jun Huang; Jiayi Ma
刊名	IEEE/CAA Journal of Automatica Sinica
	2022
卷号	9 期号:12 页码:2121-2137
关键词	Global spatial attention image fusion image registration mutual promotion semantic awareness
ISSN号	2329-9266
DOI	10.1109/JAS.2022.106082
英文摘要	Image fusion aims to integrate complementary information in source images to synthesize a fused image comprehensively characterizing the imaging scene. However, existing image fusion algorithms are only applicable to strictly aligned source images and cause severe artifacts in the fusion results when input images have slight shifts or deformations. In addition, the fusion results typically only have good visual effect, but neglect the semantic requirements of high-level vision tasks. This study incorporates image registration, image fusion, and semantic requirements of high-level vision tasks into a single framework and proposes a novel image registration and fusion method, named SuperFusion. Specifically, we design a registration network to estimate bidirectional deformation fields to rectify geometric distortions of input images under the supervision of both photometric and end-point constraints. The registration and fusion are combined in a symmetric scheme, in which while mutual promotion can be achieved by optimizing the naive fusion loss, it is further enhanced by the mono-modal consistent constraint on symmetric fusion outputs. In addition, the image fusion network is equipped with the global spatial attention mechanism to achieve adaptive feature integration. Moreover, the semantic constraint based on the pre-trained segmentation model and Lovasz-Softmax loss is deployed to guide the fusion network to focus more on the semantic requirements of high-level vision tasks. Extensive experiments on image registration, image fusion, and semantic segmentation tasks demonstrate the superiority of our SuperFusion compared to the state-of-the-art alternatives. The source code and pre-trained model are publicly available at https://github.com/Linfeng-Tang/SuperFusion.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50583]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Linfeng Tang,Yuxin Deng,Yong Ma,et al. SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness[J]. IEEE/CAA Journal of Automatica Sinica,2022,9(12):2121-2137.
APA	Linfeng Tang,Yuxin Deng,Yong Ma,Jun Huang,&Jiayi Ma.(2022).SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness.IEEE/CAA Journal of Automatica Sinica,9(12),2121-2137.
MLA	Linfeng Tang,et al."SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness".IEEE/CAA Journal of Automatica Sinica 9.12(2022):2121-2137.