Spatial-Frequency Gated Swin Transformer for Remote Sensing Single-Image Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910207411486720 |
|---|---|
| author | Hossain, Md Aminur Valkesh, Parekh Patel, Ayush V. Jethani, Yogesh Singh, Sanjay K. Banerjee, Biplab |
| author_facet | Hossain, Md Aminur Valkesh, Parekh Patel, Ayush V. Jethani, Yogesh Singh, Sanjay K. Banerjee, Biplab |
| contents | Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VENμS show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09687 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spatial-Frequency Gated Swin Transformer for Remote Sensing Single-Image Super-Resolution Hossain, Md Aminur Valkesh, Parekh Patel, Ayush V. Jethani, Yogesh Singh, Sanjay K. Banerjee, Biplab Computer Vision and Pattern Recognition Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VENμS show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution. |
| title | Spatial-Frequency Gated Swin Transformer for Remote Sensing Single-Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.09687 |