PRAN: Progressive Residual Attention Network for Super Resolution
Single image super resolution (SISR) based on deep learning has made great progress in recent years. As the method continues to improve, different network structures have been proposed to better perform SR feature extraction for reconstruction. A deep structure has a good ability to generate high-qu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9226518/ |
| _version_ | 1818349862622593024 |
|---|---|
| author | Jupeng Shi Jing Li Yan Chen Zhengjia Lu |
| author_facet | Jupeng Shi Jing Li Yan Chen Zhengjia Lu |
| author_sort | Jupeng Shi |
| collection | DOAJ |
| description | Single image super resolution (SISR) based on deep learning has made great progress in recent years. As the method continues to improve, different network structures have been proposed to better perform SR feature extraction for reconstruction. A deep structure has a good ability to generate high-quality SR features, but the complex structure may also cause problems such as hard training and overfitting. Many efforts have also been made to solve these problems, such as feedback structure and attention mechanism. However, naively applying these methods to SR networks may be useless. Hence, in this research, we took a further step by introducing progressive residual attention to generate high-quality SR images. In experiments, we compared the reconstruction results and training progress with other SR methods based on normal structures. The proposed network achieves fast convergence speed and better SR results. |
| first_indexed | 2024-12-13T18:12:42Z |
| format | Article |
| id | doaj.art-39449b1f4d884b21881651f1e08b7a57 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:12:42Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-39449b1f4d884b21881651f1e08b7a572022-12-21T23:35:55ZengIEEEIEEE Access2169-35362020-01-01818861118861910.1109/ACCESS.2020.30317199226518PRAN: Progressive Residual Attention Network for Super ResolutionJupeng Shi0https://orcid.org/0000-0002-9653-5055Jing Li1https://orcid.org/0000-0001-5664-9907Yan Chen2https://orcid.org/0000-0001-8016-4248Zhengjia Lu3https://orcid.org/0000-0001-7738-8603College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaState Grid Shanghai Electric Power Company, Shanghai, ChinaState Grid Shanghai Electric Power Company, Shanghai, ChinaSingle image super resolution (SISR) based on deep learning has made great progress in recent years. As the method continues to improve, different network structures have been proposed to better perform SR feature extraction for reconstruction. A deep structure has a good ability to generate high-quality SR features, but the complex structure may also cause problems such as hard training and overfitting. Many efforts have also been made to solve these problems, such as feedback structure and attention mechanism. However, naively applying these methods to SR networks may be useless. Hence, in this research, we took a further step by introducing progressive residual attention to generate high-quality SR images. In experiments, we compared the reconstruction results and training progress with other SR methods based on normal structures. The proposed network achieves fast convergence speed and better SR results.https://ieeexplore.ieee.org/document/9226518/Computer visionimage enhancementimage reconstructionmachine learningsuper resolution |
| spellingShingle | Jupeng Shi Jing Li Yan Chen Zhengjia Lu PRAN: Progressive Residual Attention Network for Super Resolution IEEE Access Computer vision image enhancement image reconstruction machine learning super resolution |
| title | PRAN: Progressive Residual Attention Network for Super Resolution |
| title_full | PRAN: Progressive Residual Attention Network for Super Resolution |
| title_fullStr | PRAN: Progressive Residual Attention Network for Super Resolution |
| title_full_unstemmed | PRAN: Progressive Residual Attention Network for Super Resolution |
| title_short | PRAN: Progressive Residual Attention Network for Super Resolution |
| title_sort | pran progressive residual attention network for super resolution |
| topic | Computer vision image enhancement image reconstruction machine learning super resolution |
| url | https://ieeexplore.ieee.org/document/9226518/ |
| work_keys_str_mv | AT jupengshi pranprogressiveresidualattentionnetworkforsuperresolution AT jingli pranprogressiveresidualattentionnetworkforsuperresolution AT yanchen pranprogressiveresidualattentionnetworkforsuperresolution AT zhengjialu pranprogressiveresidualattentionnetworkforsuperresolution |