A progressive framework for rotary motion deblurring
The rotary motion deblurring is an inevitable procedure when the imaging seeker is mounted in the rotating missiles. Traditional rotary motion deblurring methods suffer from ringing artifacts and noise, especially for large blur extents. To solve the above problems, we propose a progressive rotary m...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2024-02-01
|
Series: | Defence Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214914723001046 |
_version_ | 1797272497929846784 |
---|---|
author | Jinhui Qin Yong Ma Jun Huang Fan Fan You Du |
author_facet | Jinhui Qin Yong Ma Jun Huang Fan Fan You Du |
author_sort | Jinhui Qin |
collection | DOAJ |
description | The rotary motion deblurring is an inevitable procedure when the imaging seeker is mounted in the rotating missiles. Traditional rotary motion deblurring methods suffer from ringing artifacts and noise, especially for large blur extents. To solve the above problems, we propose a progressive rotary motion deblurring framework consisting of a coarse deblurring stage and a refinement stage. In the first stage, we design an adaptive blur extents factor (BE factor) to balance noise suppression and details reconstruction. And a novel deconvolution model is proposed based on BE factor. In the second stage, a triple-scale 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 locations. To 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 angles. Experimental results demonstrate that the proposed method outperforms the state-of-the-art models on synthetic and real-world rotary motion blur datasets. The code and dataset are available at https://github.com/Jinhui-Qin/RotaryDeblurring. |
first_indexed | 2024-03-07T14:29:12Z |
format | Article |
id | doaj.art-8d2f2d78c5464ed8afc43251f4b88c8b |
institution | Directory Open Access Journal |
issn | 2214-9147 |
language | English |
last_indexed | 2024-03-07T14:29:12Z |
publishDate | 2024-02-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Defence Technology |
spelling | doaj.art-8d2f2d78c5464ed8afc43251f4b88c8b2024-03-06T05:26:57ZengKeAi Communications Co., Ltd.Defence Technology2214-91472024-02-0132159172A progressive framework for rotary motion deblurringJinhui Qin0Yong Ma1Jun Huang2Fan Fan3You Du4School of Electronic Information, Wuhan University, Wuhan, 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan, 430072, ChinaCorresponding author.; School of Electronic Information, Wuhan University, Wuhan, 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan, 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan, 430072, ChinaThe rotary motion deblurring is an inevitable procedure when the imaging seeker is mounted in the rotating missiles. Traditional rotary motion deblurring methods suffer from ringing artifacts and noise, especially for large blur extents. To solve the above problems, we propose a progressive rotary motion deblurring framework consisting of a coarse deblurring stage and a refinement stage. In the first stage, we design an adaptive blur extents factor (BE factor) to balance noise suppression and details reconstruction. And a novel deconvolution model is proposed based on BE factor. In the second stage, a triple-scale 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 locations. To 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 angles. Experimental results demonstrate that the proposed method outperforms the state-of-the-art models on synthetic and real-world rotary motion blur datasets. The code and dataset are available at https://github.com/Jinhui-Qin/RotaryDeblurring.http://www.sciencedirect.com/science/article/pii/S2214914723001046Rotary motion deblurringProgressive frameworkBlur extents factorTDM-CNN |
spellingShingle | Jinhui Qin Yong Ma Jun Huang Fan Fan You Du A progressive framework for rotary motion deblurring Defence Technology Rotary motion deblurring Progressive framework Blur extents factor TDM-CNN |
title | A progressive framework for rotary motion deblurring |
title_full | A progressive framework for rotary motion deblurring |
title_fullStr | A progressive framework for rotary motion deblurring |
title_full_unstemmed | A progressive framework for rotary motion deblurring |
title_short | A progressive framework for rotary motion deblurring |
title_sort | progressive framework for rotary motion deblurring |
topic | Rotary motion deblurring Progressive framework Blur extents factor TDM-CNN |
url | http://www.sciencedirect.com/science/article/pii/S2214914723001046 |
work_keys_str_mv | AT jinhuiqin aprogressiveframeworkforrotarymotiondeblurring AT yongma aprogressiveframeworkforrotarymotiondeblurring AT junhuang aprogressiveframeworkforrotarymotiondeblurring AT fanfan aprogressiveframeworkforrotarymotiondeblurring AT youdu aprogressiveframeworkforrotarymotiondeblurring AT jinhuiqin progressiveframeworkforrotarymotiondeblurring AT yongma progressiveframeworkforrotarymotiondeblurring AT junhuang progressiveframeworkforrotarymotiondeblurring AT fanfan progressiveframeworkforrotarymotiondeblurring AT youdu progressiveframeworkforrotarymotiondeblurring |