TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers

doi:10.1109/JSTARS.2022.3143532

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 遥感图像处理团队

	TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers
	An, Tai 1,2; Zhang, Xin 1,2; Huo, Chunlei 2; Xue, Bin 1,2; Wang, Lingfeng 2; Pan, Chunhong 2
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2022
卷号	15 页码:1373-1388
关键词	Transformers Superresolution Satellites Remote sensing Task analysis Deep learning Image resolution Deep learning end-to-end networks feature extraction and fusion multiimage super-resolution (MISR) remote sensing transformers
ISSN号	1939-1404
DOI	10.1109/JSTARS.2022.3143532
通讯作者	Huo, Chunlei(clhuo@nlpr.ia.ac.cn)
英文摘要	Multiimage super-resolution (MISR), as one of the most promising directions in remote sensing, has become a needy technique in the satellite market. A sequence of images collected by satellites often has plenty of views and a long time span, so integrating multiple low-resolution views into a high-resolution image with details emerges as a challenging problem. However, most MISR methods based on deep learning cannot make full use of multiple images. Their fusion modules are incapable of adapting to an image sequence with weak temporal correlations well. To cope with these problems, we propose a novel end-to-end framework called TR-MISR. It consists of three parts: An encoder based on residual blocks, a transformer-based fusion module, and a decoder based on subpixel convolution. Specifically, by rearranging multiple feature maps into vectors, the fusion module can assign dynamic attention to the same area of different satellite images simultaneously. In addition, TR-MISR adopts an additional learnable embedding vector that fuses these vectors to restore the details to the greatest extent. TR-MISR has successfully applied the transformer to MISR tasks for the first time, notably reducing the difficulty of training the transformer by ignoring the spatial relations of image patches. Extensive experiments performed on the PROBA-V Kelvin dataset demonstrate the superiority of the proposed model that provides an effective method for transformers in other low-level vision tasks.
资助项目	National Key Research and Development Program of China[2018AAA0100400] ; National Key Research and Development Program of China[62071466] ; National Key Research and Development Program of China[61802407] ; Guangxi Natural Science Foundation[2018GXNSFBA281086]
WOS关键词	IMAGE SUPERRESOLUTION ; SUPER RESOLUTION
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000752012800003
资助机构	National Key Research and Development Program of China ; Guangxi Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/47358]
专题	自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者	Huo, Chunlei
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	An, Tai,Zhang, Xin,Huo, Chunlei,et al. TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2022,15:1373-1388.
APA	An, Tai,Zhang, Xin,Huo, Chunlei,Xue, Bin,Wang, Lingfeng,&Pan, Chunhong.(2022).TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,15,1373-1388.
MLA	An, Tai,et al."TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 15(2022):1373-1388.