Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution
Most of the existing remote sensing image super-resolution (SR) methods based on deep learning tend to learn the mapping from low-resolution (LR) images to high-resolution (HR) images directly. But they ignore the potential structure and texture consistency of LR and HR spaces, which cause the loss...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10423125/ |
| _version_ | 1797268051526156288 |
|---|---|
| author | Kanghui Zhao Tao Lu Yanduo Zhang Junjun Jiang Zhongyuan Wang Zixiang Xiong |
| author_facet | Kanghui Zhao Tao Lu Yanduo Zhang Junjun Jiang Zhongyuan Wang Zixiang Xiong |
| author_sort | Kanghui Zhao |
| collection | DOAJ |
| description | Most of the existing remote sensing image super-resolution (SR) methods based on deep learning tend to learn the mapping from low-resolution (LR) images to high-resolution (HR) images directly. But they ignore the potential structure and texture consistency of LR and HR spaces, which cause the loss of high-frequency information and produce artifacts. A structure-texture dual preserving method is proposed to solve this problem and generate pleasing details. Specifically, we propose a novel edge prior enhancement strategy that uses the edges of LR images and the proposed interactive supervised attention module (ISAM) to guide SR reconstruction. First, we introduce the LR edge map as a prior structural expression for SR reconstruction, which further enhances the SR process with edge preservation capability. In addition, to obtain finer texture edge information, we propose a novel ISAM in order to correct the initial LR edge map with high-frequency information. By introducing LR edges and ISAM-corrected HR edges, we build LR–HR edge mapping to preserve the consistency of LR and HR edge structure and texture, which provides supervised information for SR reconstruction. Finally, we explore the salient features of the image and its edges in the ascending space, and restored the difference between LR and HR images by residual and dense learning. A large number of experimental results on Draper and NWPU-RESISC45 datasets show that our model is superior to several advanced SR algorithms in both objective and subjective image quality. |
| first_indexed | 2024-03-07T14:05:28Z |
| format | Article |
| id | doaj.art-f3d1d48d483146d1ab622993307cdb6b |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-25T01:26:20Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-f3d1d48d483146d1ab622993307cdb6b2024-03-09T00:00:07ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01175527554010.1109/JSTARS.2024.336288010423125Structure-Texture Dual Preserving for Remote Sensing Image Super ResolutionKanghui Zhao0https://orcid.org/0000-0002-6666-645XTao Lu1https://orcid.org/0000-0001-8117-2012Yanduo Zhang2https://orcid.org/0000-0002-7490-0939Junjun Jiang3https://orcid.org/0000-0002-5694-505XZhongyuan Wang4https://orcid.org/0000-0002-9796-488XZixiang Xiong5https://orcid.org/0000-0002-4714-3311Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, ChinaHubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, ChinaComputer School, Hubei University of Arts and Science, Xiangyang, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin, ChinaNational Engineering Research Center for Multimedia Software (NERCMS), School of Computer Science, Wuhan University, Wuhan, ChinaDepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USAMost of the existing remote sensing image super-resolution (SR) methods based on deep learning tend to learn the mapping from low-resolution (LR) images to high-resolution (HR) images directly. But they ignore the potential structure and texture consistency of LR and HR spaces, which cause the loss of high-frequency information and produce artifacts. A structure-texture dual preserving method is proposed to solve this problem and generate pleasing details. Specifically, we propose a novel edge prior enhancement strategy that uses the edges of LR images and the proposed interactive supervised attention module (ISAM) to guide SR reconstruction. First, we introduce the LR edge map as a prior structural expression for SR reconstruction, which further enhances the SR process with edge preservation capability. In addition, to obtain finer texture edge information, we propose a novel ISAM in order to correct the initial LR edge map with high-frequency information. By introducing LR edges and ISAM-corrected HR edges, we build LR–HR edge mapping to preserve the consistency of LR and HR edge structure and texture, which provides supervised information for SR reconstruction. Finally, we explore the salient features of the image and its edges in the ascending space, and restored the difference between LR and HR images by residual and dense learning. A large number of experimental results on Draper and NWPU-RESISC45 datasets show that our model is superior to several advanced SR algorithms in both objective and subjective image quality.https://ieeexplore.ieee.org/document/10423125/Edge enhancedinteractive supervised attention module (ISAM)remote sensing imagesuper-resolution (SR) reconstruction |
| spellingShingle | Kanghui Zhao Tao Lu Yanduo Zhang Junjun Jiang Zhongyuan Wang Zixiang Xiong Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Edge enhanced interactive supervised attention module (ISAM) remote sensing image super-resolution (SR) reconstruction |
| title | Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution |
| title_full | Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution |
| title_fullStr | Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution |
| title_full_unstemmed | Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution |
| title_short | Structure-Texture Dual Preserving for Remote Sensing Image Super Resolution |
| title_sort | structure texture dual preserving for remote sensing image super resolution |
| topic | Edge enhanced interactive supervised attention module (ISAM) remote sensing image super-resolution (SR) reconstruction |
| url | https://ieeexplore.ieee.org/document/10423125/ |
| work_keys_str_mv | AT kanghuizhao structuretexturedualpreservingforremotesensingimagesuperresolution AT taolu structuretexturedualpreservingforremotesensingimagesuperresolution AT yanduozhang structuretexturedualpreservingforremotesensingimagesuperresolution AT junjunjiang structuretexturedualpreservingforremotesensingimagesuperresolution AT zhongyuanwang structuretexturedualpreservingforremotesensingimagesuperresolution AT zixiangxiong structuretexturedualpreservingforremotesensingimagesuperresolution |