Adaptive deep residual network for single image super-resolution
Abstract In recent years, deep learning has achieved great success in the field of image processing. In the single image super-resolution (SISR) task, the convolutional neural network (CNN) extracts the features of the image through deeper layers, and has achieved impressive results. In this paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-01-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s41095-019-0158-8 |
| _version_ | 1811270803940966400 |
|---|---|
| author | Shuai Liu Ruipeng Gang Chenghua Li Ruixia Song |
| author_facet | Shuai Liu Ruipeng Gang Chenghua Li Ruixia Song |
| author_sort | Shuai Liu |
| collection | DOAJ |
| description | Abstract In recent years, deep learning has achieved great success in the field of image processing. In the single image super-resolution (SISR) task, the convolutional neural network (CNN) extracts the features of the image through deeper layers, and has achieved impressive results. In this paper, we propose a single image super-resolution model based on Adaptive Deep Residual named as ADR-SR, which uses the Input Output Same Size (IOSS) structure, and releases the dependence of upsampling layers compared with the existing SR methods. Specifically, the key element of our model is the Adaptive Residual Block (ARB), which replaces the commonly used constant factor with an adaptive residual factor. The experiments prove the effectiveness of our ADR-SR model, which can not only reconstruct images with better visual effects, but also get better objective performances. |
| first_indexed | 2024-04-12T22:08:40Z |
| format | Article |
| id | doaj.art-7a505fefe5464e21b9ae9d2ac7b50a74 |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-04-12T22:08:40Z |
| publishDate | 2020-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-7a505fefe5464e21b9ae9d2ac7b50a742022-12-22T03:14:50ZengSpringerOpenComputational Visual Media2096-04332096-06622020-01-015439140110.1007/s41095-019-0158-8Adaptive deep residual network for single image super-resolutionShuai Liu0Ruipeng Gang1Chenghua Li2Ruixia Song3North China University of TechnologyNorth China University of TechnologyInstitute of Automation, Chinese Academy of SciencesNorth China University of TechnologyAbstract In recent years, deep learning has achieved great success in the field of image processing. In the single image super-resolution (SISR) task, the convolutional neural network (CNN) extracts the features of the image through deeper layers, and has achieved impressive results. In this paper, we propose a single image super-resolution model based on Adaptive Deep Residual named as ADR-SR, which uses the Input Output Same Size (IOSS) structure, and releases the dependence of upsampling layers compared with the existing SR methods. Specifically, the key element of our model is the Adaptive Residual Block (ARB), which replaces the commonly used constant factor with an adaptive residual factor. The experiments prove the effectiveness of our ADR-SR model, which can not only reconstruct images with better visual effects, but also get better objective performances.https://doi.org/10.1007/s41095-019-0158-8single image super-resolution (SISR)adaptive deep residual networkdeep learning |
| spellingShingle | Shuai Liu Ruipeng Gang Chenghua Li Ruixia Song Adaptive deep residual network for single image super-resolution Computational Visual Media single image super-resolution (SISR) adaptive deep residual network deep learning |
| title | Adaptive deep residual network for single image super-resolution |
| title_full | Adaptive deep residual network for single image super-resolution |
| title_fullStr | Adaptive deep residual network for single image super-resolution |
| title_full_unstemmed | Adaptive deep residual network for single image super-resolution |
| title_short | Adaptive deep residual network for single image super-resolution |
| title_sort | adaptive deep residual network for single image super resolution |
| topic | single image super-resolution (SISR) adaptive deep residual network deep learning |
| url | https://doi.org/10.1007/s41095-019-0158-8 |
| work_keys_str_mv | AT shuailiu adaptivedeepresidualnetworkforsingleimagesuperresolution AT ruipenggang adaptivedeepresidualnetworkforsingleimagesuperresolution AT chenghuali adaptivedeepresidualnetworkforsingleimagesuperresolution AT ruixiasong adaptivedeepresidualnetworkforsingleimagesuperresolution |