DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
Open Access
- 14 November 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (22) , 4251
Abstract
Transformer-based methods have demonstrated impressive performance in image super-resolution tasks. However, when applied to large-scale Earth observation images, the existing transformers encounter two significant challenges: (1) insufficient consideration of spatial correlation between adjacent ground objects; and (2) performance bottlenecks due to the underutilization of the upsample module. To address these issues, we propose a novel distance-enhanced strip attention transformer (DESAT). The DESAT integrates distance priors, easily obtainable from remote sensing images, into the strip window self-attention mechanism to capture spatial correlations more effectively. To further enhance the transfer of deep features into high-resolution outputs, we designed an attention-enhanced upsample block, which combines the pixel shuffle layer with an attention-based upsample branch implemented through the overlapping window self-attention mechanism. Additionally, to better simulate real-world scenarios, we constructed a new cross-sensor super-resolution dataset using Gaofen-6 satellite imagery. Extensive experiments on both simulated and real-world remote sensing datasets demonstrate that the DESAT outperforms state-of-the-art models by up to 1.17 dB along with superior qualitative results. Furthermore, the DESAT achieves more competitive performance in real-world tasks, effectively balancing spatial detail reconstruction and spectral transform, making it highly suitable for practical remote sensing super-resolution applications.Keywords
Funding Information
- National Natural Science Foundation of China (62101531, 61731022, 2019QZKK030701, XDA19090300)
- Second Tibetan Plateau Scientific Expedition and Research Program (62101531, 61731022, 2019QZKK030701, XDA19090300)
- Strategic Priority Research Program of the Chinese Academy of Sciences (62101531, 61731022, 2019QZKK030701, XDA19090300)
This publication has 43 references indexed in Scilit:
- A novel weakly-supervised method based on the segment anything model for seamless transition from classification to segmentation: A case study in segmenting latent photovoltaic locationsInternational Journal of Applied Earth Observation and Geoinformation, 2024
- A Weakly Supervised Semantic Segmentation Framework for Medium-Resolution Forest Classification With Noisy Labels and GF-1 WFV ImagesIEEE Transactions on Geoscience and Remote Sensing, 2024
- TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-ResolutionIEEE Transactions on Image Processing, 2024
- Dual-domain strip attention for image restorationNeural Networks, 2023
- Image super-resolution: A comprehensive review, recent trends, challenges and applicationsInformation Fusion, 2022
- Real-world single image super-resolution: A brief reviewInformation Fusion, 2022
- Land-cover classification with high-resolution remote sensing images using transferable deep modelsRemote Sensing of Environment, 2020
- Object detection in optical remote sensing images: A survey and a new benchmarkISPRS Journal of Photogrammetry and Remote Sensing, 2020
- AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002