Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network
Image super-resolution technology can reduce the cost and complexity of acquiring high-resolution infrared thermal images. In this study, we propose a novel end-to-end single infrared super-resolution network based on shifted full-scale non-local residual block. A full-scale non-local mechanism is f...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10713218/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533418296311808 |
|---|---|
| author | Honghong Lu Zhenhua Li |
| author_facet | Honghong Lu Zhenhua Li |
| author_sort | Honghong Lu |
| collection | DOAJ |
| description | Image super-resolution technology can reduce the cost and complexity of acquiring high-resolution infrared thermal images. In this study, we propose a novel end-to-end single infrared super-resolution network based on shifted full-scale non-local residual block. A full-scale non-local mechanism is first proposed to enhance the channel and spatial dependencies of the intra-frame feature map. Based on this mechanism, a shifted full-scale non-local residual block is constructed. By confining full-scale non-local to local windows while allowing for shifted-window connectivity, full-scale non-local residual block solves the problem that existed non-local structures are difficult to be reused and serves as backbone for super-resolution network. Qualitative and quantitative evaluation results show that our method has better performance on benchmark datasets of Set5, Set14, BSD100, and the self-built infrared dataset under the up-sample factor of <inline-formula> <tex-math notation="LaTeX">$\times 2$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\times 3$ </tex-math></inline-formula>, and <inline-formula> <tex-math notation="LaTeX">$\times 4$ </tex-math></inline-formula>. |
| format | Article |
| id | doaj-art-7fe2953ce1994bb8bd4d3e49406b7028 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7fe2953ce1994bb8bd4d3e49406b70282025-01-16T00:01:35ZengIEEEIEEE Access2169-35362024-01-011217852317853510.1109/ACCESS.2024.346474710713218Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local NetworkHonghong Lu0Zhenhua Li1Faculty of Science, Nanjing University of Science and Technology, Nanjing, Jiangsu, ChinaFaculty of Science, Nanjing University of Science and Technology, Nanjing, Jiangsu, ChinaImage super-resolution technology can reduce the cost and complexity of acquiring high-resolution infrared thermal images. In this study, we propose a novel end-to-end single infrared super-resolution network based on shifted full-scale non-local residual block. A full-scale non-local mechanism is first proposed to enhance the channel and spatial dependencies of the intra-frame feature map. Based on this mechanism, a shifted full-scale non-local residual block is constructed. By confining full-scale non-local to local windows while allowing for shifted-window connectivity, full-scale non-local residual block solves the problem that existed non-local structures are difficult to be reused and serves as backbone for super-resolution network. Qualitative and quantitative evaluation results show that our method has better performance on benchmark datasets of Set5, Set14, BSD100, and the self-built infrared dataset under the up-sample factor of <inline-formula> <tex-math notation="LaTeX">$\times 2$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\times 3$ </tex-math></inline-formula>, and <inline-formula> <tex-math notation="LaTeX">$\times 4$ </tex-math></inline-formula>.https://ieeexplore.ieee.org/document/10713218/Convolution neural networkfull-scale non-localself-attention mechanismshifted full-scale non-local residual blocksingle infrared super-solution |
| spellingShingle | Honghong Lu Zhenhua Li Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network IEEE Access Convolution neural network full-scale non-local self-attention mechanism shifted full-scale non-local residual block single infrared super-solution |
| title | Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network |
| title_full | Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network |
| title_fullStr | Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network |
| title_full_unstemmed | Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network |
| title_short | Single Infrared Super-Resolution via a Shifted Full-Scale Non-Local Network |
| title_sort | single infrared super resolution via a shifted full scale non local network |
| topic | Convolution neural network full-scale non-local self-attention mechanism shifted full-scale non-local residual block single infrared super-solution |
| url | https://ieeexplore.ieee.org/document/10713218/ |
| work_keys_str_mv | AT honghonglu singleinfraredsuperresolutionviaashiftedfullscalenonlocalnetwork AT zhenhuali singleinfraredsuperresolutionviaashiftedfullscalenonlocalnetwork |