GSDAT-Net: Enhancing Image Super-Resolution with Grid-Spatial Dual Attention Hybrid Transformer
Sensors · 22.07.2026 · 26 (14) · 4634
DOI: 10.3390/s26144634 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.07.2026. Verfasst von Yunqiang Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Microelectronics Industry-Education Integration, Lanzhou University of Technology, Lanzhou 730050, China. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Gansu Province.
Abstract (Originalsprache)
Image super-resolution (SR) is a fundamental task in computer vision that aims to recover high-fidelity details from low-resolution images. To address the limitations of existing Transformer-based SR methods, this paper introduces GSDAT-Net, a grid-spatial dual-attention-driven residual hybrid Transformer. By integrating Grid Attention Block (GAB), an Enhanced Spatial Attention (ESA) module, and SwinV2 Transformer layers (S2TL), GSDAT-Net extracts multi-scale features and improves local and global feature representation. Extensive experiments demonstrate that GSDAT-Net achieves competitive reconstruction accuracy and visual quality compared with the selected methods, with a maximum PSNR improvement of up to 0.15 dB on benchmark datasets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Microelectronics Industry-Education Integration, Lanzhou University of Technology, Lanzhou 730050, China.
- School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
ORCID-Profile: Yunqiang Liu
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Gansu Province
Zitieren
APA
Liu, Y., Wei, T., & Wang, J. (2026). GSDAT-Net: Enhancing Image Super-Resolution with Grid-Spatial Dual Attention Hybrid Transformer. Sensors, 26(14), 4634. https://doi.org/10.3390/s26144634
Vancouver
Liu Y, Wei T, Wang J. GSDAT-Net: Enhancing Image Super-Resolution with Grid-Spatial Dual Attention Hybrid Transformer. Sensors. 2026;26(14):4634. doi:10.3390/s26144634
BibTeX
@article{Liu2026,
author = {Liu, Yunqiang and Wei, Ting and Wang, Jinhua},
title = {GSDAT-Net: Enhancing Image Super-Resolution with Grid-Spatial Dual Attention Hybrid Transformer},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4634},
doi = {10.3390/s26144634}
}
EUVIMED