Super-resolution reconstruction based on two-stage residual neural network
With the constant update of deep learning technology, the super-resolution reconstruction technology based on deep learning has also attained a significant breakthrough. This paper primarily discusses the integration of deep learning and super-resolution reconstruction techniques. Regarding the appl...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827021000815 |
| _version_ | 1819174281853009920 |
|---|---|
| author | Lin Dong Kohei Inoue |
| author_facet | Lin Dong Kohei Inoue |
| author_sort | Lin Dong |
| collection | DOAJ |
| description | With the constant update of deep learning technology, the super-resolution reconstruction technology based on deep learning has also attained a significant breakthrough. This paper primarily discusses the integration of deep learning and super-resolution reconstruction techniques. Regarding the application of deep learning in super-resolution reconstruction, the improvement is focused on the two dimensions of algorithm efficiency and reconstruction effect. On the basis of the currently available neural network algorithms, this paper puts forward the two-stage residual super-resolution reconstruction network structure. Thereinto, the improvement is mainly embodied in the modification of the image feature extraction network modules and the increase of the residual block into two stages. It is experimentally evidenced by algorithm simulation that the two-stage residual network in this paper shows a certain extent of improvement for the super-resolution reconstruction effect compared with the related methods. |
| first_indexed | 2024-12-22T20:36:29Z |
| format | Article |
| id | doaj.art-e1459308bdd0448aa398bff2d022ddf3 |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-12-22T20:36:29Z |
| publishDate | 2021-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-e1459308bdd0448aa398bff2d022ddf32022-12-21T18:13:27ZengElsevierMachine Learning with Applications2666-82702021-12-016100162Super-resolution reconstruction based on two-stage residual neural networkLin Dong0Kohei Inoue1Department of Communication Design Science, Kyushu University, 4-9-1, Shiobaru, Minami-ku, Fukuoka, 815-8540, JapanCorresponding author.; Department of Communication Design Science, Kyushu University, 4-9-1, Shiobaru, Minami-ku, Fukuoka, 815-8540, JapanWith the constant update of deep learning technology, the super-resolution reconstruction technology based on deep learning has also attained a significant breakthrough. This paper primarily discusses the integration of deep learning and super-resolution reconstruction techniques. Regarding the application of deep learning in super-resolution reconstruction, the improvement is focused on the two dimensions of algorithm efficiency and reconstruction effect. On the basis of the currently available neural network algorithms, this paper puts forward the two-stage residual super-resolution reconstruction network structure. Thereinto, the improvement is mainly embodied in the modification of the image feature extraction network modules and the increase of the residual block into two stages. It is experimentally evidenced by algorithm simulation that the two-stage residual network in this paper shows a certain extent of improvement for the super-resolution reconstruction effect compared with the related methods.http://www.sciencedirect.com/science/article/pii/S2666827021000815Super-resolution reconstructionDeep learningTwo-stage residual network |
| spellingShingle | Lin Dong Kohei Inoue Super-resolution reconstruction based on two-stage residual neural network Machine Learning with Applications Super-resolution reconstruction Deep learning Two-stage residual network |
| title | Super-resolution reconstruction based on two-stage residual neural network |
| title_full | Super-resolution reconstruction based on two-stage residual neural network |
| title_fullStr | Super-resolution reconstruction based on two-stage residual neural network |
| title_full_unstemmed | Super-resolution reconstruction based on two-stage residual neural network |
| title_short | Super-resolution reconstruction based on two-stage residual neural network |
| title_sort | super resolution reconstruction based on two stage residual neural network |
| topic | Super-resolution reconstruction Deep learning Two-stage residual network |
| url | http://www.sciencedirect.com/science/article/pii/S2666827021000815 |
| work_keys_str_mv | AT lindong superresolutionreconstructionbasedontwostageresidualneuralnetwork AT koheiinoue superresolutionreconstructionbasedontwostageresidualneuralnetwork |