SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion
Multi-source remote sensing spatiotemporal fusion aims to enhance the temporal continuity of high-spatial, low-temporal-resolution images. In recent years, deep learning-based spatiotemporal fusion methods have achieved significant progress in this field. However, existing methods face three major c...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/13/2315 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704588965314560 |
|---|---|
| author | Zhaoxu Ma Wenxing Bao Wei Feng Xiaowu Zhang Xuan Ma Kewen Qu |
| author_facet | Zhaoxu Ma Wenxing Bao Wei Feng Xiaowu Zhang Xuan Ma Kewen Qu |
| author_sort | Zhaoxu Ma |
| collection | DOAJ |
| description | Multi-source remote sensing spatiotemporal fusion aims to enhance the temporal continuity of high-spatial, low-temporal-resolution images. In recent years, deep learning-based spatiotemporal fusion methods have achieved significant progress in this field. However, existing methods face three major challenges. First, large differences in spatial resolution among heterogeneous remote sensing images hinder the reconstruction of high-quality texture details. Second, most current deep learning-based methods prioritize spatial information while overlooking spectral information. Third, these methods often depend on complex network architectures, resulting in high computational costs. To address the aforementioned challenges, this article proposes a Sparse Fast Transformer fusion method based on Generative Adversarial Network (SFT-GAN). First, the method introduces a multi-scale feature extraction and fusion architecture to capture temporal variation features and spatial detail features across multiple scales. A channel attention mechanism is subsequently designed to integrate these heterogeneous features adaptively. Secondly, two information compensation modules are introduced: detail compensation module, which enhances high-frequency information to improve the fidelity of spatial details; spectral compensation module, which improves spectral fidelity by leveraging the intrinsic spectral correlation of the image. In addition, the proposed sparse fast transformer significantly reduces both the computational and memory complexity of the method. Experimental results on four publicly available benchmark datasets showed that the proposed SFT-GAN achieved the best performance compared with state-of-the-art methods in fusion accuracy while reducing computational cost by approximately 70%. Additional classification experiments further validated the practical effectiveness of SFT-GAN. Overall, this approach presents a new paradigm for balancing accuracy and efficiency in spatiotemporal fusion. |
| format | Article |
| id | doaj-art-db9e97687eff4049bd7138d0f765a0e3 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-db9e97687eff4049bd7138d0f765a0e32025-08-20T03:16:42ZengMDPI AGRemote Sensing2072-42922025-07-011713231510.3390/rs17132315SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal FusionZhaoxu Ma0Wenxing Bao1Wei Feng2Xiaowu Zhang3Xuan Ma4Kewen Qu5School of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaDepartment of Remote Sensing Science and Technology, School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaMulti-source remote sensing spatiotemporal fusion aims to enhance the temporal continuity of high-spatial, low-temporal-resolution images. In recent years, deep learning-based spatiotemporal fusion methods have achieved significant progress in this field. However, existing methods face three major challenges. First, large differences in spatial resolution among heterogeneous remote sensing images hinder the reconstruction of high-quality texture details. Second, most current deep learning-based methods prioritize spatial information while overlooking spectral information. Third, these methods often depend on complex network architectures, resulting in high computational costs. To address the aforementioned challenges, this article proposes a Sparse Fast Transformer fusion method based on Generative Adversarial Network (SFT-GAN). First, the method introduces a multi-scale feature extraction and fusion architecture to capture temporal variation features and spatial detail features across multiple scales. A channel attention mechanism is subsequently designed to integrate these heterogeneous features adaptively. Secondly, two information compensation modules are introduced: detail compensation module, which enhances high-frequency information to improve the fidelity of spatial details; spectral compensation module, which improves spectral fidelity by leveraging the intrinsic spectral correlation of the image. In addition, the proposed sparse fast transformer significantly reduces both the computational and memory complexity of the method. Experimental results on four publicly available benchmark datasets showed that the proposed SFT-GAN achieved the best performance compared with state-of-the-art methods in fusion accuracy while reducing computational cost by approximately 70%. Additional classification experiments further validated the practical effectiveness of SFT-GAN. Overall, this approach presents a new paradigm for balancing accuracy and efficiency in spatiotemporal fusion.https://www.mdpi.com/2072-4292/17/13/2315spatiotemporal fusionremote sensingmulti-source datagenerative adversarial network (GAN)transformer |
| spellingShingle | Zhaoxu Ma Wenxing Bao Wei Feng Xiaowu Zhang Xuan Ma Kewen Qu SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion Remote Sensing spatiotemporal fusion remote sensing multi-source data generative adversarial network (GAN) transformer |
| title | SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion |
| title_full | SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion |
| title_fullStr | SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion |
| title_full_unstemmed | SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion |
| title_short | SFT-GAN: Sparse Fast Transformer Fusion Method Based on GAN for Remote Sensing Spatiotemporal Fusion |
| title_sort | sft gan sparse fast transformer fusion method based on gan for remote sensing spatiotemporal fusion |
| topic | spatiotemporal fusion remote sensing multi-source data generative adversarial network (GAN) transformer |
| url | https://www.mdpi.com/2072-4292/17/13/2315 |
| work_keys_str_mv | AT zhaoxuma sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion AT wenxingbao sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion AT weifeng sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion AT xiaowuzhang sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion AT xuanma sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion AT kewenqu sftgansparsefasttransformerfusionmethodbasedonganforremotesensingspatiotemporalfusion |