Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution
Recently, with the rise and progress of convolutional neural networks (CNNs), CNN-based remote-sensing image super-resolution (RSSR) methods have gained considerable advancement and showed great power for image reconstruction tasks. However, most of these methods cannot handle well the enormous numb...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10049097/ |
| _version_ | 1797861339729756160 |
|---|---|
| author | Zheng Wang Yanwei Zhao Jiacheng Chen |
| author_facet | Zheng Wang Yanwei Zhao Jiacheng Chen |
| author_sort | Zheng Wang |
| collection | DOAJ |
| description | Recently, with the rise and progress of convolutional neural networks (CNNs), CNN-based remote-sensing image super-resolution (RSSR) methods have gained considerable advancement and showed great power for image reconstruction tasks. However, most of these methods cannot handle well the enormous number of objects with different scales contained in remote-sensing images and thus limits super-resolution performance. To address these issues, we propose a multiscale fast Fourier transform (FFT) based attention network (MSFFTAN), which employs a multiinput U-shape structure as backbone for accurate RSSR. Specifically, we carefully design an FFT-based residual block consisting of an image domain branch and a Fourier domain branch to extract local details and global structures simultaneously. In addition, a local–global channel attention block is developed to further enhance the reconstruction ability of small targets. Finally, we present a branch gated selective block to adaptively explore and aggregate features from multiple scales and depths. Extensive experiments on two public datasets have demonstrated the superiority of MSFFTAN over the state-of-the-art (SOAT) approaches in aspects of both quantitative metrics and visual quality. The peak signal-to-noise ratio of our network is 1.5 dB higher than the SOAT method on the UCMerced LandUse with downscaling factor 2. |
| first_indexed | 2024-04-09T22:00:38Z |
| format | Article |
| id | doaj.art-38046d4ea8c0491b9b3b6f3a6747024c |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-09T22:00:38Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-38046d4ea8c0491b9b3b6f3a6747024c2023-03-23T23:00:07ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01162728274010.1109/JSTARS.2023.324656410049097Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-ResolutionZheng Wang0Yanwei Zhao1Jiacheng Chen2https://orcid.org/0000-0001-7384-7972School of Computer Computational Science, Hangzhou City University, Hangzhou, ChinaSchool of Engineering, Hangzhou City University, Hangzhou, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, ChinaRecently, with the rise and progress of convolutional neural networks (CNNs), CNN-based remote-sensing image super-resolution (RSSR) methods have gained considerable advancement and showed great power for image reconstruction tasks. However, most of these methods cannot handle well the enormous number of objects with different scales contained in remote-sensing images and thus limits super-resolution performance. To address these issues, we propose a multiscale fast Fourier transform (FFT) based attention network (MSFFTAN), which employs a multiinput U-shape structure as backbone for accurate RSSR. Specifically, we carefully design an FFT-based residual block consisting of an image domain branch and a Fourier domain branch to extract local details and global structures simultaneously. In addition, a local–global channel attention block is developed to further enhance the reconstruction ability of small targets. Finally, we present a branch gated selective block to adaptively explore and aggregate features from multiple scales and depths. Extensive experiments on two public datasets have demonstrated the superiority of MSFFTAN over the state-of-the-art (SOAT) approaches in aspects of both quantitative metrics and visual quality. The peak signal-to-noise ratio of our network is 1.5 dB higher than the SOAT method on the UCMerced LandUse with downscaling factor 2.https://ieeexplore.ieee.org/document/10049097/Attention mechanismfast Fourier transform (FFT)multiinput mechanismremote-sensing imagesuper-resolution |
| spellingShingle | Zheng Wang Yanwei Zhao Jiacheng Chen Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism fast Fourier transform (FFT) multiinput mechanism remote-sensing image super-resolution |
| title | Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution |
| title_full | Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution |
| title_fullStr | Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution |
| title_full_unstemmed | Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution |
| title_short | Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution |
| title_sort | multi scale fast fourier transform based attention network for remote sensing image super resolution |
| topic | Attention mechanism fast Fourier transform (FFT) multiinput mechanism remote-sensing image super-resolution |
| url | https://ieeexplore.ieee.org/document/10049097/ |
| work_keys_str_mv | AT zhengwang multiscalefastfouriertransformbasedattentionnetworkforremotesensingimagesuperresolution AT yanweizhao multiscalefastfouriertransformbasedattentionnetworkforremotesensingimagesuperresolution AT jiachengchen multiscalefastfouriertransformbasedattentionnetworkforremotesensingimagesuperresolution |