Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution
Remote Sensing · 04.10.2024 · 16 (19) · 3695
DOI: 10.3390/rs16193695 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 04.10.2024. Verfasst von Ziang Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chongqing Natural Science Foundation Innovation and Development Joint Fund Project, Key Industrial Innovation Chain Project in Industrial Domain of Shaanxi Province.
Abstract (Originalsprache)
Remote-sensing images typically feature large dimensions and contain repeated texture patterns. To effectively capture finer details and encode comprehensive information, feature-extraction networks with larger receptive fields are essential for remote-sensing image super-resolution tasks. However, mainstream methods based on stacked Transformer modules suffer from limited receptive fields due to fixed window sizes, impairing long-range dependency capture and fine-grained texture reconstruction. In this paper, we propose a spatial-frequency joint attention network based on multi-window fusion (MWSFA). Specifically, our approach introduces a multi-window fusion strategy, which merges windows with similar textures to allow self-attention mechanisms to capture long-range dependencies effectively, therefore expanding the receptive field of the feature extractor. Additionally, we incorporate a frequency-domain self-attention branch in parallel with the original Transformer architecture. This branch leverages the global characteristics of the frequency domain to further extend the receptive field, enabling more comprehensive self-attention calculations across different frequency bands and better utilization of consistent frequency information. Extensive experiments on both synthetic and real remote-sensing datasets demonstrate that our method achieves superior visual reconstruction effects and higher evaluation metrics compared to other super-resolution methods.
Förderung
- National Natural Science Foundation of China
- Chongqing Natural Science Foundation Innovation and Development Joint Fund Project
- Key Industrial Innovation Chain Project in Industrial Domain of Shaanxi Province
Zitieren
APA
Li, Z., Lu, W., Wang, Z., Hu, J., Zhang, Z., & He, L. (2024). Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution. Remote Sensing, 16(19), 3695. https://doi.org/10.3390/rs16193695
Vancouver
Li Z, Lu W, Wang Z, Hu J, Zhang Z, He L. Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution. Remote Sensing. 2024;16(19):3695. doi:10.3390/rs16193695
BibTeX
@article{Li2024,
author = {Li, Ziang and Lu, Wen and Wang, Zhaoyang and Hu, Jian and Zhang, Zeming and He, Lihuo},
title = {Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {19},
pages = {3695},
doi = {10.3390/rs16193695}
}
EUVIMED