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

By Linfeng Tang, Yuxin Deng, Yong Ma, Jun Huang, Jiayi Ma. IEEE/CAA Journal of Automatica Sinica, 2022

422 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/5c57e3536c29321e9ef2090db7c03f3d50f48989

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Radu Timofte
2. Luc Van Gool
3. Yulun Zhang
4. Xiao-Jun Wu
5. Chen Change Loy
6. Ming-Hsuan Yang
7. Hui Li
8. Lei Zhang

In Media Technology

1. Radu Timofte
2. Luc Van Gool
3. Yulun Zhang
4. Xiao-Jun Wu
5. Yiannis Demiris
6. Xingchen Zhang
7. Hui Li
8. Chao Dong

Citations in the corpus

• CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach (2024, background): “It is often utilized in multi-modal tasks where information from di ff erent modalities needs to be integrated to solve a specific problem, such as image fusion [56][57][58], and image registration based fusion method [59][60].”
• CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (2022, methodology): “Many methods have been developed to tackle the MMIF challenges in recent years [35, 41, 44, 55, 73, 74, 82].”
• Visible and Infrared Image Fusion Using Deep Learning (2023, methodology): “It is also worth investigating image fusion, registration, and downstream applications together, as done by Tang et al. [199].”