Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution
Achieving balance between efficiency and performance is a key problem for convolution neural network (CNN)-based single-image super-resolution (SISR) algorithms. Existing methods tend to directly output high-resolution (HR) pixels or residuals to reconstruct the HR image and focus a lot of attention...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/9/1348 |
| _version_ | 1797505205825175552 |
|---|---|
| author | Wei Wu Wen Xu Bolun Zheng Aiai Huang Chenggang Yan |
| author_facet | Wei Wu Wen Xu Bolun Zheng Aiai Huang Chenggang Yan |
| author_sort | Wei Wu |
| collection | DOAJ |
| description | Achieving balance between efficiency and performance is a key problem for convolution neural network (CNN)-based single-image super-resolution (SISR) algorithms. Existing methods tend to directly output high-resolution (HR) pixels or residuals to reconstruct the HR image and focus a lot of attention on designing powerful CNN backbones. However, this reconstruction way requires the CNN backbone to have good ability to fit the mapping function from LR pixels to HR pixels, which certainly held these methods back from achieving extreme efficiency and from working in embedded environments. In this work, we propose a novel distribution learning architecture to estimate the local distribution and reconstruct HR pixels by sampling the local distribution with the corresponding 2D coordinates. We also improve the backbone structure to better support the proposed distribution learning architecture. The experimental results demonstrate that the proposed method achieves state-of-the-art performance for extremely efficient SISR and exhibits a good balance between efficiency and performance. |
| first_indexed | 2024-03-10T04:15:18Z |
| format | Article |
| id | doaj.art-b1531a383dd0457e982d662d28003732 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T04:15:18Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b1531a383dd0457e982d662d280037322023-11-23T08:02:18ZengMDPI AGElectronics2079-92922022-04-01119134810.3390/electronics11091348Learning Local Distribution for Extremely Efficient Single-Image Super-ResolutionWei Wu0Wen Xu1Bolun Zheng2Aiai Huang3Chenggang Yan4School of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaAchieving balance between efficiency and performance is a key problem for convolution neural network (CNN)-based single-image super-resolution (SISR) algorithms. Existing methods tend to directly output high-resolution (HR) pixels or residuals to reconstruct the HR image and focus a lot of attention on designing powerful CNN backbones. However, this reconstruction way requires the CNN backbone to have good ability to fit the mapping function from LR pixels to HR pixels, which certainly held these methods back from achieving extreme efficiency and from working in embedded environments. In this work, we propose a novel distribution learning architecture to estimate the local distribution and reconstruct HR pixels by sampling the local distribution with the corresponding 2D coordinates. We also improve the backbone structure to better support the proposed distribution learning architecture. The experimental results demonstrate that the proposed method achieves state-of-the-art performance for extremely efficient SISR and exhibits a good balance between efficiency and performance.https://www.mdpi.com/2079-9292/11/9/1348image super-resolutionlocal distribution modelextreme efficientmulti-layer neural network |
| spellingShingle | Wei Wu Wen Xu Bolun Zheng Aiai Huang Chenggang Yan Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution Electronics image super-resolution local distribution model extreme efficient multi-layer neural network |
| title | Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution |
| title_full | Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution |
| title_fullStr | Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution |
| title_full_unstemmed | Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution |
| title_short | Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution |
| title_sort | learning local distribution for extremely efficient single image super resolution |
| topic | image super-resolution local distribution model extreme efficient multi-layer neural network |
| url | https://www.mdpi.com/2079-9292/11/9/1348 |
| work_keys_str_mv | AT weiwu learninglocaldistributionforextremelyefficientsingleimagesuperresolution AT wenxu learninglocaldistributionforextremelyefficientsingleimagesuperresolution AT bolunzheng learninglocaldistributionforextremelyefficientsingleimagesuperresolution AT aiaihuang learninglocaldistributionforextremelyefficientsingleimagesuperresolution AT chenggangyan learninglocaldistributionforextremelyefficientsingleimagesuperresolution |