A progressive framework for rotary motion deblurring
作者机构:School of Electronic InformationWuhan UniversityWuhan430072China
出 版 物:《Defence Technology(防务技术)》 (Defence Technology)
年 卷 期:2024年第32卷第2期
页 面:159-172页
核心收录:
学科分类:08[工学] 081105[工学-导航、制导与控制] 0804[工学-仪器科学与技术] 0811[工学-控制科学与工程]
基 金:the National Natural Science Foundation of China under Grant 62075169,Grant 62003247,and Grant 62061160370 the Hubei Province Key Research and Development Program under Grant 2021BBA235 the Zhuhai Basic and Applied Basic Research Foundation under Grant ZH22017003200010PWC
主 题:Rotary motion deblurring Progressive framework Blur extents factor TDM-CNN
摘 要:The rotary motion deblurring is an inevitable procedure when the imaging seeker is mounted in the rotating *** rotary motion deblurring methods suffer from ringing artifacts and noise,especially for large blur *** solve the above problems,we propose a progressive rotary motion deblurring framework consisting of a coarse deblurring stage and a refinement *** the first stage,we design an adaptive blur extents factor(BE factor)to balance noise suppression and details *** a novel deconvolution model is proposed based on BE *** the second stage,a triplescale deformable module CNN(TDM-CNN)is designed to reduce the ringing artifacts,which can exploit the 2D information of an image and adaptively adjust spatial sampling *** establish a standard evaluation benchmark,a real-world rotary motion blur dataset is proposed and released,which includes rotary blurred images and corresponding ground truth images with different blur *** results demonstrate that the proposed method outperforms the state-of-the-art models on synthetic and real-world rotary motion blur *** code and dataset are available at https://***/JinhuiQin/RotaryDeblurring.