DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism
Reference image based super-resolution methods (RefSR) have made rapid and remarkable progress in the field of image super-resolution (SR) in recent years by introducing additional high-resolution (HR) images to enhance the recovery of low-resolution (LR) images. The existing RefSR methods can rely...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9772484/ |
| _version_ | 1818231490399436800 |
|---|---|
| author | Xin Liu Jing Li Tingting Duan Jiangtao Li Ye Wang |
| author_facet | Xin Liu Jing Li Tingting Duan Jiangtao Li Ye Wang |
| author_sort | Xin Liu |
| collection | DOAJ |
| description | Reference image based super-resolution methods (RefSR) have made rapid and remarkable progress in the field of image super-resolution (SR) in recent years by introducing additional high-resolution (HR) images to enhance the recovery of low-resolution (LR) images. The existing RefSR methods can rely on implicit correspondence matching to transfer the HR texture from the reference image (Ref) to compensate for the information loss in the input image. However, the differences between low-resolution input images and high-resolution reference images still affects the effective utilization of Ref images, so it is an important challenge to make full use of the information in Ref images to improve the SR performance. In this paper, we propose an image super-resolution method based on dual-view supervised learning and multi-attention mechanism (DSMA). It enhances the learning of important detail features of Ref images and weakens the interference of noisy information by introducing the multi-attention mechanism, while employing dual-view supervision to motivate the network to learn more accurate feature representations. Quantitative and qualitative experiments on these benchmarks, i.e., CUFED5, Urban100 and Manga109, show that DSMA outperforms the state-of-the-art baselines with significant improvements. |
| first_indexed | 2024-12-12T10:51:13Z |
| format | Article |
| id | doaj.art-dd3fea9cfdb14f1f9e7506b7054d0a62 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T10:51:13Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dd3fea9cfdb14f1f9e7506b7054d0a622022-12-22T00:26:46ZengIEEEIEEE Access2169-35362022-01-0110546495465910.1109/ACCESS.2022.31741949772484DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention MechanismXin Liu0https://orcid.org/0000-0001-9460-7855Jing Li1Tingting Duan2Jiangtao Li3Ye Wang4College 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 Electronic Commerce Company Ltd., Beijing, ChinaState Grid Electronic Commerce Company Ltd., Beijing, ChinaNanjing Nari Information Communication Technology Company Ltd., Nanjing, ChinaReference image based super-resolution methods (RefSR) have made rapid and remarkable progress in the field of image super-resolution (SR) in recent years by introducing additional high-resolution (HR) images to enhance the recovery of low-resolution (LR) images. The existing RefSR methods can rely on implicit correspondence matching to transfer the HR texture from the reference image (Ref) to compensate for the information loss in the input image. However, the differences between low-resolution input images and high-resolution reference images still affects the effective utilization of Ref images, so it is an important challenge to make full use of the information in Ref images to improve the SR performance. In this paper, we propose an image super-resolution method based on dual-view supervised learning and multi-attention mechanism (DSMA). It enhances the learning of important detail features of Ref images and weakens the interference of noisy information by introducing the multi-attention mechanism, while employing dual-view supervision to motivate the network to learn more accurate feature representations. Quantitative and qualitative experiments on these benchmarks, i.e., CUFED5, Urban100 and Manga109, show that DSMA outperforms the state-of-the-art baselines with significant improvements.https://ieeexplore.ieee.org/document/9772484/Computer visionimage enhancementimage reconstructionmachine learningsuper resolution |
| spellingShingle | Xin Liu Jing Li Tingting Duan Jiangtao Li Ye Wang DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism IEEE Access Computer vision image enhancement image reconstruction machine learning super resolution |
| title | DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism |
| title_full | DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism |
| title_fullStr | DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism |
| title_full_unstemmed | DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism |
| title_short | DSMA: Reference-Based Image Super-Resolution Method Based on Dual-View Supervised Learning and Multi-Attention Mechanism |
| title_sort | dsma reference based image super resolution method based on dual view supervised learning and multi attention mechanism |
| topic | Computer vision image enhancement image reconstruction machine learning super resolution |
| url | https://ieeexplore.ieee.org/document/9772484/ |
| work_keys_str_mv | AT xinliu dsmareferencebasedimagesuperresolutionmethodbasedondualviewsupervisedlearningandmultiattentionmechanism AT jingli dsmareferencebasedimagesuperresolutionmethodbasedondualviewsupervisedlearningandmultiattentionmechanism AT tingtingduan dsmareferencebasedimagesuperresolutionmethodbasedondualviewsupervisedlearningandmultiattentionmechanism AT jiangtaoli dsmareferencebasedimagesuperresolutionmethodbasedondualviewsupervisedlearningandmultiattentionmechanism AT yewang dsmareferencebasedimagesuperresolutionmethodbasedondualviewsupervisedlearningandmultiattentionmechanism |