模式识别与人工智能
Monday, Apr. 7, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (6): 557-569    DOI: 10.16451/j.cnki.issn1003-6059.202406006
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Multi-granularity Dynamic Scene Image Deblurring Network Based on Deep Fusion of Frequency Domain and Spatial Domain Features
CHEN Zihan1,2, ZHANG Hongyun1,2, MIAO Duoqian1,2, CAI Kecan1,2
1. College of Electronic and Information Engineering, Tongji University, Shanghai 201804;
2. Key Laboratory of Embedded Systems and Service Computing of Ministry of Education, Tongji University, Shanghai 201804

Download: PDF (4922 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Dynamic scene image deblurring is highly ill-posed, and the relative motion between the camera and the photographed target makes the blur non-uniform. Most existing deep learning methods focus on the spatial domain processing and neglect the potential contribution of the frequency domain to structural and detail recovery, leading to poor deblurring results. To solve the problems, the role of frequency domain information in image deblurring is rethought, and multi-granularity dynamic scene image deblurring network based on deep fusion of frequency domain and spatial domain features is proposed. Firstly, a frequency domain gated frequency-spatial feature deep fusion module is proposed to fully explore the correlation between spatial domain and frequency domain information. The redundancy of the fused features is reduced and the complementarity between the two domains is enhanced. Secondly, based on the proposed module, a multi-granularity network is constructed, and it fully utilizes different granularity information in the spatial domain and frequency domain for coarse-to-fine image deblurring. Finally, to solve the problem of frequency domain feature map resolution mismatch caused by different input feature map sizes during training and testing, a frequency domain resolution adaptive testing strategy is adopted to maintain the consistency of frequency changes. Experiments conducted on synthetic datasets, GoPro and HIDE, and a real dataset, RealBlur, demonstrate the proposed algorithm outperforms existing advanced algorithms in reconstructing clear images with competitive parameters and efficiency.
Key wordsDynamic Scene Image Deblurring      Multi-granularity Deblurring Network      Frequency Domain Gating      Deep Fusion of Frequency and Space Features      Adaptive Testing     
Received: 28 May 2024     
ZTFLH: TP 389.1  
Fund:National Key Research and Development Program of China(No.2022YFB3104700), National Natural Science Foun-dation of China(No.62076182,62376198), Natural Science Foun?dation of Shanghai(No.22ZR1466700)
Corresponding Authors: ZHANG Hongyun, Ph.D., associate professor. Her research interests include principal curve algorithm, gra-nular computing and computer vision.   
About author:: CHEN Zihan, Master student. Her research interests include computer vision and granular computing. MIAO Duoqian, Ph.D., professor. His research interests include machine learning, data mining, granular computing, artificial intelligence and text image processing.CAI Kecan, Ph.D. candidate. Her research interests include computer vision and granular computing.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHEN Zihan
ZHANG Hongyun
MIAO Duoqian
CAI Kecan
Cite this article:   
CHEN Zihan,ZHANG Hongyun,MIAO Duoqian等. Multi-granularity Dynamic Scene Image Deblurring Network Based on Deep Fusion of Frequency Domain and Spatial Domain Features[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(6): 557-569.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202406006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I6/557
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn