• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Li, Xiaoguang (Li, Xiaoguang.) | Yang, Feifan (Yang, Feifan.) | Huang, Jianglu (Huang, Jianglu.) | Zhuo, Li (Zhuo, Li.)

Indexed by:

Scopus SCIE

Abstract:

Images captured in a real scene usually suffer from complex non-uniform degradation, which includes both global and local blurs. It is difficult to handle the complex blur variances by a unified processing model. We propose a global-local blur disentangling network, which can effectively extract global and local blur features via two branches. A phased training scheme is designed to disentangle the global and local blur features, that is the branches are trained with task-specific datasets, respectively. A branch attention mechanism is introduced to dynamically fuse global and local features. Complex blurry images are used to train the attention module and the reconstruction module. The visualized feature maps of different branches indicated that our dual-branch network can decouple the global and local blur features efficiently. Experimental results show that the proposed dual-branch blur disentangling network can improve both the subjective and objective deblurring effects for real captured images.

Keyword:

branch attention dual-branch disentangling network

Author Community:

  • [ 1 ] [Li, Xiaoguang]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 2 ] [Yang, Feifan]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 3 ] [Huang, Jianglu]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 4 ] [Zhuo, Li]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 5 ] [Li, Xiaoguang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 6 ] [Yang, Feifan]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 7 ] [Huang, Jianglu]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 8 ] [Zhuo, Li]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Li, Xiaoguang]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China;;[Li, Xiaoguang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

APPLIED SCIENCES-BASEL

Year: 2021

Issue: 5

Volume: 11

2 . 7 0 0

JCR@2022

ESI Discipline: ENGINEERING;

ESI HC Threshold:87

JCR Journal Grade:2

Cited Count:

WoS CC Cited Count: 1

SCOPUS Cited Count: 1

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Online/Total:493/5316695
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.