IEEE Transactions on Geoscience and Remote Sensing · 2024 · 25 citations · 46 references
ComputingComputer ScienceComputer VisionMachine LearningRemote SensingAttention NetworksDeep LearningDigital Image ProcessingRemote Sensing Image AnalysisRemote Sensing ImageryRepresentation LearningConvolutional Neural NetworksDeep Feature ExtractionDeep Feature LearningImage Super-resolutionMulti-scale FeaturesRemote Sensing ApplicationsRemote Sensing Image FeaturesSuper-resolution
Remote Sensing Image Super-Resolution (RSISR) techniques play a crucial role in various remote sensing applications. However, deep learning-based methods applied to RSISR encounter difficulties in learning complex features of remote sensing images and modeling long-term correlations between pixels. This study proposes a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-Scale Sliding Window Attention Generation Adversarial Network (MSWAGAN)</i> , which combines the advantages of Convolutional Neural Networks (CNN) and Transformers to overcome these limitations. The MSWAGAN consists of three main parts. In the shallow feature extraction part, CNN is used to extract shallow features from remote sensing images. The deep feature extraction part is divided into two stages. Firstly, a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-scale sliding window attention (MSWA)</i> is designed to replace the multi-head attention (MHA) in the Transformer. MSWA can learn local multi-scale complex features of remote sensing images without increasing the number of parameters in MHA. Then, the Transformer is utilized to learn global image features and model the long-range correlations between pixels. The image reconstruction part utilizes sub-pixel convolution for feature upsampling. Furthermore, in order to extend the application of super-resolution remote sensing images, a cross-sensor real multi-spectral RSISR dataset consisting of Landsat-8 (L8) and Sentinel-2 (S2) images was constructed, and a series of experiments to improve the spatial resolution of L8 images from 30m to 10m in B, G, R and Near Infrared (NIR) bands were conducted. Experimental results demonstrate that our method outperforms some of the latest SR methods.
46
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Xception: Deep Learning with Depthwise Separable Convolutions
François Chollet · 2017 · 19K citations
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Richard Zhang, Phillip Isola, Alexei A. Efros et al. · 2018 · 12.4K citations