A General Spatial-Frequency Learning Framework for Multimodal Image Fusion
Nanyang Technological University · Aerospace Information Research Institute · +11 more institutions
Abstract
Multimodal image fusion involves tasks like pan-sharpening and depth super-resolution. Both tasks aim to generate high-resolution target images by fusing the complementary information from the texture-rich guidance and low-resolution target counterparts. They are inborn with reconstructing high-frequency information. Despite their inherent frequency domain connection, most existing methods only operate solely in the spatial domain and rarely explore the solutions in the frequency domain. This study addresses this limitation by proposing solutions in both the spatial and frequency domains. We devise a Spatial-Frequency Information Integration Network, abbreviated as SFINet for this purpose. The SFINet includes…
Citation impact
- FWCI
- 37.34
- Percentile
- 100%
- References
- 56
Authors
7- MZMan ZhouCorresponding
Nanyang Technological University, Aerospace Information Research Institute
- JHJie Huang
University of Science and Technology of China
- KYKeyu Yan
University of Science and Technology of China
- DHDanfeng Hong
Chinese Academy of Sciences, Aerospace Information Research Institute, University of Chinese Academy of Sciences
- XJXiuping Jia
University of Canberra, UNSW Sydney
Topics & keywords
- Computer science
- Artificial intelligence
- Frequency domain
- Convolution (computer science)
- Domain (mathematical analysis)
- Pattern recognition (psychology)
- Spatial analysis
- Sharpening