Logo image
MSFA-RSISR: Multi-scale and Fourier Attention for Remote Sensing Image Super-Resolution
Conference proceeding   Peer reviewed

MSFA-RSISR: Multi-scale and Fourier Attention for Remote Sensing Image Super-Resolution

Z Xie, J Wang, Y Du, Xiaochen Liu and W Song
Pattern Recognition and Computer Vision: 8th Chinese Conference, PRCV 2025, Shanghai, China, October 15–18, 2025, Proceedings, Part VIII, Vol.16279, pp.544-558
Lecture Notes in Computer Science, 16279
Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2025 (Shanghai, 15/10/2025–18/10/2025)
2025
Handle:
https://hdl.handle.net/10863/52317

Abstract

Data-driven Artificial Intelligence (D2AI)
Although Vision Transformers based on window mechanisms have shown remarkable performance in remote sensing image super-resolution (RSISR), the traditional window mechanism limits the interaction of global information. Moreover, the large range and rich high-frequency information of remote sensing images make reconstruction more challenging. To address these issues, this paper proposes a new RSISR framework called MSFA-RSISR based on the SwinTransformer: It innovatively introduces Frequency Fourier Block (FFB) to enhance high-frequency feature extraction; designs a Multi-scale Fusion Block (MSFB) to optimize the balance between global and local features through multi-scale recursion and feature compression; and employs a three-stage training strategy from natural images to remote sensing images to efficiently integrate cross-domain knowledge. Experiments on multiple datasets demonstrate that this method significantly improves the reconstruction of high-frequency details and the recovery of global structures.
url
https://link.springer.com/chapter/10.1007/978-981-95-5682-3_38View

Details

Metrics

1 Record Views
Logo image