Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention
The random noise and anisotropic motion of atmospheric turbulence can cause different degradation patterns, which make images of space targets observed from ground-based stations severely disturbed. In recent years, benefit from the development of convolutional neural networks (CNNs), a large number...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9216133/ |
| _version_ | 1818349832054505472 |
|---|---|
| author | Peijian Zhu Chunzhi Xie Zhisheng Gao |
| author_facet | Peijian Zhu Chunzhi Xie Zhisheng Gao |
| author_sort | Peijian Zhu |
| collection | DOAJ |
| description | The random noise and anisotropic motion of atmospheric turbulence can cause different degradation patterns, which make images of space targets observed from ground-based stations severely disturbed. In recent years, benefit from the development of convolutional neural networks (CNNs), a large number of effective end-to-end methods were proposed to restore images. However, a single-frame method whose input is just a single image can hardly achieve a further improvement for the restoration image due to the diversified degradation patterns of space-target images. In this paper, we proposed a multi-branch network with a multi-frame input to restore space-target images. The multi-frame input contains space-target images which own different degradation patterns at different moments. In this way, we can fully use the complementary information between input frames. And in this network, two effective technologies are introduced: one is the full resolution convolution module which extracts features by using convolutional layers with different dilation rates to keep feature information complete; the other is the branch-attention module which is used to pass effective information between different branches of the network. Furthermore, we demonstrated the effectiveness of our method by comparing it with those state-of-the-art methods. |
| first_indexed | 2024-12-13T18:12:13Z |
| format | Article |
| id | doaj.art-c654767b550e4aa9bbd635c2625a5c63 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:12:13Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c654767b550e4aa9bbd635c2625a5c632022-12-21T23:35:56ZengIEEEIEEE Access2169-35362020-01-01818381318382510.1109/ACCESS.2020.30293569216133Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-AttentionPeijian Zhu0https://orcid.org/0000-0002-7686-8602Chunzhi Xie1https://orcid.org/0000-0001-9901-2754Zhisheng Gao2https://orcid.org/0000-0002-0470-8861School of Computer and Software Engineering, Xihua University, Chengdu, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu, ChinaThe random noise and anisotropic motion of atmospheric turbulence can cause different degradation patterns, which make images of space targets observed from ground-based stations severely disturbed. In recent years, benefit from the development of convolutional neural networks (CNNs), a large number of effective end-to-end methods were proposed to restore images. However, a single-frame method whose input is just a single image can hardly achieve a further improvement for the restoration image due to the diversified degradation patterns of space-target images. In this paper, we proposed a multi-branch network with a multi-frame input to restore space-target images. The multi-frame input contains space-target images which own different degradation patterns at different moments. In this way, we can fully use the complementary information between input frames. And in this network, two effective technologies are introduced: one is the full resolution convolution module which extracts features by using convolutional layers with different dilation rates to keep feature information complete; the other is the branch-attention module which is used to pass effective information between different branches of the network. Furthermore, we demonstrated the effectiveness of our method by comparing it with those state-of-the-art methods.https://ieeexplore.ieee.org/document/9216133/Multi-frame image restorationmulti-branch networkself-attentionbranch-attentionfull resolution convolutionimages of space targets |
| spellingShingle | Peijian Zhu Chunzhi Xie Zhisheng Gao Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention IEEE Access Multi-frame image restoration multi-branch network self-attention branch-attention full resolution convolution images of space targets |
| title | Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention |
| title_full | Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention |
| title_fullStr | Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention |
| title_full_unstemmed | Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention |
| title_short | Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention |
| title_sort | multi frame blind restoration for image of space target with frc and branch attention |
| topic | Multi-frame image restoration multi-branch network self-attention branch-attention full resolution convolution images of space targets |
| url | https://ieeexplore.ieee.org/document/9216133/ |
| work_keys_str_mv | AT peijianzhu multiframeblindrestorationforimageofspacetargetwithfrcandbranchattention AT chunzhixie multiframeblindrestorationforimageofspacetargetwithfrcandbranchattention AT zhishenggao multiframeblindrestorationforimageofspacetargetwithfrcandbranchattention |